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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 34249
    Prev
    Next
    INDEX
    Explanations

    sports and political references, especially related to players, teams, and transactions

    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
    314
    +0.10
    0.6%
    627
    +0.09
    0.5%
    50
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.10
    0.04
    273
    +0.09
    0.12
    267
    +0.08
    0.12
    Negative Logits
     [|
    -0.59
     \"
    -0.57
     pc
    -0.56
     ..."
    -0.53
     ÏĦ
    -0.53
     diffusion
    -0.51
     sacrific
    -0.51
     mono
    -0.49
     BO
    -0.48
     hol
    -0.47
    POSITIVE LOGITS
    resa
    1.07
    odore
    0.83
    mosp
    0.74
    lahoma
    0.74
    ndra
    0.72
    ldon
    0.65
    alyst
    0.65
    patrick
    0.65
    gency
    0.63
    nir
    0.63
    Activations Density 5.549%

    No Known Activations