Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 45181
    Prev
    Next
    INDEX
    Explanations

    verbs indicating the action of adding something or making an addition to a specific context

    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
    +0.24
    1.1%
    274
    +0.13
    0.6%
    623
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.24
    0.27
    608
    +0.13
    0.20
    761
    +0.12
    0.12
    Negative Logits
    rior
    -0.70
    yah
    -0.67
    baum
    -0.66
    NING
    -0.65
    walking
    -0.65
    zing
    -0.63
     WATCHED
    -0.63
    ograms
    -0.63
    grim
    -0.63
     Zel
    -0.62
    POSITIVE LOGITS
    endum
    1.11
    itionally
    0.97
    itional
    0.95
    ictions
    0.95
     insult
    0.95
    itivity
    0.86
    ition
    0.83
     thereto
    0.82
    itions
    0.82
    added
    0.80
    Activations Density 12.965%

    No Known Activations