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. 9864
    Prev
    Next
    INDEX
    Explanations

    specific food-related terms and culinary references

    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
    303
    +0.04
    0.4%
    200
    +0.03
    0.4%
    256
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    110
    +0.04
    0.01
    192
    +0.03
    0.01
    67
    +0.03
    0.01
    Negative Logits
    inelli
    -0.26
    eele
    -0.26
     buttons
    -0.26
     Reps
    -0.26
     Weir
    -0.26
     advoc
    -0.25
     Wiggins
    -0.25
    enhagen
    -0.24
    uggest
    -0.24
     Giles
    -0.24
    POSITIVE LOGITS
    CLE
    0.28
    apeake
    0.27
    atsu
    0.27
    ONG
    0.27
    ship
    0.27
    pton
    0.26
     atmosphere
    0.26
    ming
    0.26
    nova
    0.26
     Explosion
    0.26
    Activations Density 0.004%

    No Known Activations