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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 32944
    Prev
    Next
    INDEX
    Explanations

    strong activations related to historical or political figures and events

    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
    336
    +0.12
    0.5%
    678
    +0.11
    0.5%
    163
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    154
    +0.12
    0.11
    556
    +0.11
    0.08
    293
    +0.11
    0.09
    Negative Logits
    eers
    -0.79
    BALL
    -0.76
    e
    -0.72
     Homo
    -0.68
     Grizzlies
    -0.67
     reversible
    -0.67
    eq
    -0.67
     Tasman
    -0.66
    cens
    -0.66
    eus
    -0.64
    POSITIVE LOGITS
    acht
    0.99
    acking
    0.90
    onds
    0.90
    ud
    0.90
    utable
    0.88
    anging
    0.87
    mann
    0.85
    uty
    0.84
    mare
    0.83
    azard
    0.83
    Activations Density 6.398%

    No Known Activations