© 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. 14259
    Prev
    Next
    INDEX
    Explanations

    expressions related to personal identity or self-awareness

    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
    +0.22
    1.0%
    393
    +0.16
    0.7%
    102
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.22
    0.27
    102
    +0.16
    0.27
    566
    +0.14
    0.20
    Negative Logits
     Refresh
    -0.76
    heny
    -0.71
    idates
    -0.67
    uish
    -0.67
     Highlands
    -0.67
     Highlights
    -0.66
     refresh
    -0.64
     Yards
    -0.63
    oldown
    -0.60
     Indust
    -0.60
    POSITIVE LOGITS
     supposed
    1.10
     destined
    0.97
     gonna
    0.93
     able
    0.93
     going
    0.90
     doing
    0.86
     presented
    0.81
     experiencing
    0.80
     meant
    0.80
     weakest
    0.79
    Activations Density 8.113%

    No Known Activations