© 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. 34843
    Prev
    Next
    INDEX
    Explanations

    keywords and syntax related to programming and coding

    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
    100
    +0.11
    0.5%
    706
    +0.11
    0.5%
    446
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.11
    -0.02
    127
    +0.11
    0.07
    401
    +0.10
    0.12
    Negative Logits
    psey
    -0.93
    hower
    -0.84
    osures
    -0.76
    nesday
    -0.75
    zhou
    -0.71
    INGTON
    -0.71
     Hoo
    -0.69
    icit
    -0.69
    jri
    -0.69
    rompt
    -0.69
    POSITIVE LOGITS
    aceae
    0.84
    "},"
    0.81
    / 
    0.78
     guiActiveUnfocused
    0.75
    idae
    0.74
     ItemLevel
    0.74
     });
    0.73
    "}],"
    0.72
     entity
    0.72
    .""
    0.72
    Activations Density 11.472%

    No Known Activations