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 L0 E2E Recon
    5. 2-RES_SLEFR-AJT
    6. 5411
    Prev
    Next
    INDEX
    Explanations

    references to teeth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_slefr-ajt/2-res_slefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    615
    +0.10
    0.5%
    255
    +0.09
    0.5%
    715
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    129
    +0.10
    0.02
    605
    +0.09
    0.02
    258
    +0.09
    0.02
    Negative Logits
    toggle
    -0.65
    owski
    -0.63
    recomm
    -0.62
    ISS
    -0.61
     Osw
    -0.59
     AFL
    -0.59
    KER
    -0.58
     Bulldogs
    -0.57
    Indiana
    -0.56
    altern
    -0.56
    POSITIVE LOGITS
     teeth
    0.89
     tooth
    0.85
    uity
    0.73
     chewing
    0.70
     restraining
    0.70
     clen
    0.69
     restraint
    0.68
    pick
    0.66
     belts
    0.66
     biting
    0.65
    Activations Density 0.014%

    No Known Activations