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. 4218
    Prev
    Next
    INDEX
    Explanations

    strings related to politics and government controversies

    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
    373
    +0.11
    0.6%
    101
    +0.09
    0.5%
    129
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    299
    +0.11
    0.08
    101
    +0.09
    0.12
    150
    +0.09
    0.04
    Negative Logits
    isu
    -0.60
    alan
    -0.58
    izard
    -0.52
     Lima
    -0.52
     Lak
    -0.52
    pta
    -0.51
     Kaiser
    -0.51
    ÄŁ
    -0.50
     slic
    -0.50
     Ares
    -0.49
    POSITIVE LOGITS
    hower
    0.75
    ochond
    0.72
    achusetts
    0.68
    emonic
    0.63
    aceutical
    0.63
    nown
    0.61
    gage
    0.60
    feel
    0.60
    piece
    0.58
     miracles
    0.58
    Activations Density 3.363%

    No Known Activations