© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 32077
    Prev
    Next
    INDEX
    Explanations

    terms related to biology - specifically, mitochondrial function and biosynthesis, as well as medical terms such as ATP, RNA, and hemoglobin

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    496
    +0.11
    0.6%
    644
    +0.09
    0.5%
    476
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.26
    326
    +0.09
    0.22
    709
    +0.09
    0.11
    Negative Logits
    ciples
    -0.57
    cap
    -0.55
    interstitial
    -0.54
     exception
    -0.52
    iple
    -0.52
    caps
    -0.50
    SHIP
    -0.49
     cannibal
    -0.49
    yss
    -0.49
    verbal
    -0.48
    POSITIVE LOGITS
    ria
    0.74
    ivable
    0.64
    anas
    0.64
    kees
    0.63
    ols
    0.62
    ility
    0.61
    ills
    0.59
    rian
    0.58
    ania
    0.57
    iolet
    0.57
    Activations Density 6.652%

    No Known Activations