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. 13370
    Prev
    Next
    INDEX
    Explanations

    sequences related to specific historical events, possibly involving political or military actions

    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
    71
    +0.08
    0.5%
    647
    +0.07
    0.5%
    658
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    488
    +0.08
    0.12
    547
    +0.07
    0.04
    237
    +0.07
    0.07
    Negative Logits
    roph
    -0.49
    acea
    -0.48
    abyte
    -0.47
    Syn
    -0.45
    WN
    -0.44
    yer
    -0.43
    roma
    -0.42
    oggle
    -0.42
    amera
    -0.42
    onom
    -0.42
    POSITIVE LOGITS
    forth
    0.77
     onwards
    0.65
     onward
    0.61
    wagon
    0.58
    hower
    0.55
    abouts
    0.53
    ither
    0.52
    ments
    0.52
    backer
    0.51
    raft
    0.49
    Activations Density 9.995%

    No Known Activations