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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13164
    Prev
    Next
    INDEX
    Explanations

    chemical names and related terms

    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
    75
    +0.14
    0.6%
    31
    +0.13
    0.5%
    472
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.14
    0.31
    138
    +0.13
    0.28
    288
    +0.12
    0.27
    Negative Logits
    glers
    -1.16
    giving
    -1.08
    elson
    -0.97
    enegger
    -0.91
    enhagen
    -0.84
    llers
    -0.84
    terson
    -0.82
    XT
    -0.81
    OPLE
    -0.79
    erv
    -0.79
    POSITIVE LOGITS
     chloride
    1.25
     iod
    0.94
     bleach
    0.92
    umph
    0.90
    chlor
    0.89
     cyan
    0.88
     bacter
    0.86
     disinfect
    0.86
    inatory
    0.85
    ifax
    0.85
    Activations Density 9.603%

    No Known Activations