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. 5388
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals and organizations

    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
    710
    +0.13
    0.6%
    202
    +0.12
    0.5%
    57
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.08
    326
    +0.12
    0.06
    289
    +0.11
    0.04
    Negative Logits
    arb
    -0.80
    bot
    -0.79
    osc
    -0.75
    eled
    -0.74
    ober
    -0.72
    aways
    -0.71
    gom
    -0.70
    ocrats
    -0.69
    arter
    -0.68
    oglu
    -0.68
    POSITIVE LOGITS
    inventoryQuantity
    0.86
    vati
    0.82
    velength
    0.80
    terness
    0.78
    é¾įåĸļ士
    0.78
     seiz
    0.76
    iversal
    0.76
    afety
    0.75
    issan
    0.74
    ĸļ
    0.72
    Activations Density 0.410%

    No Known Activations