© 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. 32929
    Prev
    Next
    INDEX
    Explanations

    emphatic expressions and opinions

    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
    157
    +0.14
    0.6%
    155
    +0.13
    0.5%
    139
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    242
    +0.14
    0.09
    393
    +0.13
    0.17
    279
    +0.12
    0.08
    Negative Logits
     Loft
    -0.77
     resid
    -0.70
     sep
    -0.68
    cel
    -0.66
     indist
    -0.65
     fullest
    -0.65
     pulp
    -0.65
    lez
    -0.65
    jer
    -0.65
    yi
    -0.65
    POSITIVE LOGITS
    iances
    1.05
    iance
    0.99
    igators
    0.87
    tests
    0.85
    igator
    0.83
    atta
    0.82
    udes
    0.82
    wing
    0.77
    ocating
    0.76
    enges
    0.75
    Activations Density 6.426%

    No Known Activations