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. 40111
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and references, especially within the context of American sports leagues and events

    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
    554
    +0.06
    0.5%
    71
    +0.06
    0.5%
    479
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.06
    0.04
    176
    +0.06
    0.04
    311
    +0.06
    -0.06
    Negative Logits
    bread
    -0.44
    tons
    -0.42
    lers
    -0.41
    lands
    -0.41
    ies
    -0.40
    eled
    -0.40
    utenberg
    -0.40
    flush
    -0.40
     overd
    -0.38
    gone
    -0.38
    POSITIVE LOGITS
    WAYS
    0.56
    BILITY
    0.48
    HAEL
    0.46
    TOR
    0.44
     Palestin
    0.42
     Mehran
    0.42
     Motorsport
    0.41
    ITE
    0.40
    pmwiki
    0.40
     TODAY
    0.39
    Activations Density 8.404%

    No Known Activations