© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 34727
    Prev
    Next
    INDEX
    Explanations

    characters' names as well as themes of sci-fi or action narrative passages

    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
    526
    +0.05
    0.5%
    195
    +0.05
    0.5%
    409
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    582
    +0.05
    0.04
    343
    +0.05
    0.07
    746
    +0.05
    0.02
    Negative Logits
    ablishment
    -0.41
    upon
    -0.38
     Belief
    -0.36
     Petraeus
    -0.33
    hovah
    -0.32
    affles
    -0.32
    Ö¼
    -0.31
     liar
    -0.31
     Journalists
    -0.30
    enance
    -0.30
    POSITIVE LOGITS
    eties
    0.49
    ãĥ¼ãĤ¯
    0.46
     Skywalker
    0.43
    ny
    0.43
    itus
    0.42
    strument
    0.42
    sson
    0.42
    sha
    0.42
    avin
    0.42
    eteenth
    0.41
    Activations Density 9.423%

    No Known Activations