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. 5404
    Prev
    Next
    INDEX
    Explanations

    references to specific types of stones

    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
    288
    +0.15
    0.7%
    699
    +0.14
    0.6%
    601
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    667
    +0.15
    0.03
    699
    +0.14
    0.01
    30
    +0.11
    0.02
    Negative Logits
    ntil
    -0.80
    ornia
    -0.78
    unct
    -0.74
    ARI
    -0.73
    mercial
    -0.73
     largeDownload
    -0.70
    alg
    -0.70
    acy
    -0.69
     Prev
    -0.68
    olulu
    -0.67
    POSITIVE LOGITS
     stone
    1.20
    Stone
    1.12
     stones
    1.11
     Stone
    0.99
     Stones
    0.91
    hill
    0.90
     castles
    0.89
    stones
    0.89
    bats
    0.87
    stone
    0.87
    Activations Density 0.041%

    No Known Activations