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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 34433
    Prev
    Next
    INDEX
    Explanations

    text related to football scouting, player training, game strategizing or media commentary

    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
    +0.11
    0.7%
    702
    +0.08
    0.5%
    179
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.11
    0.40
    107
    +0.08
    0.05
    702
    +0.08
    0.14
    Negative Logits
     cas
    -0.43
     Frozen
    -0.41
     signing
    -0.40
     reign
    -0.39
     enthusiastic
    -0.39
     epilepsy
    -0.37
     gluten
    -0.37
     damp
    -0.37
     ice
    -0.36
     proactive
    -0.36
    POSITIVE LOGITS
    depending
    0.55
    isms
    0.52
    ãĥ³ãĤ¸
    0.51
    whatever
    0.48
    SPONSORED
    0.48
    ãĥĦ
    0.47
    EST
    0.46
     respectively
    0.45
    skip
    0.44
    -+-+
    0.44
    Activations Density 26.855%

    No Known Activations