© 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. 40649
    Prev
    Next
    INDEX
    Explanations

    phrases introducing personal knowledge or understanding

    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
    447
    +0.21
    0.9%
    230
    +0.13
    0.5%
    750
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    230
    +0.21
    0.07
    8
    +0.13
    0.09
    373
    +0.12
    -0.12
    Negative Logits
    isco
    -0.98
     sidx
    -0.89
    onding
    -0.87
    acies
    -0.87
    taboola
    -0.84
    interstitial
    -0.79
    cific
    -0.79
    ishers
    -0.77
    aez
    -0.77
    inse
    -0.76
    POSITIVE LOGITS
     firsthand
    0.98
     nothing
    0.86
    ledged
    0.84
    ledge
    0.83
     how
    0.83
    nothing
    0.79
     what
    0.74
     exactly
    0.72
     plenty
    0.72
     beforehand
    0.71
    Activations Density 5.748%

    No Known Activations