© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 27217
    Prev
    Next
    INDEX
    Explanations

    references to keratin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.24
    1.4%
    71
    +0.19
    1.1%
    433
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.24
    0.01
    271
    +0.19
    0.00
    269
    +0.12
    0.01
    Negative Logits
     fois
    -1.69
     Microsoft
    -1.64
    ķ
    -1.60
    ı
    -1.59
    pez
    -1.55
    ±
    -1.51
     particular
    -1.49
    ¯
    -1.49
    Ħ
    -1.46
    Ŀ
    -1.46
    POSITIVE LOGITS
    ics
    1.72
    varn
    1.72
    istan
    1.55
    idium
    1.53
    ospheric
    1.49
    imedia
    1.48
     herself
    1.46
    atics
    1.46
    tight
    1.44
    ISPR
    1.44
    Activations Density 4.656%

    No Known Activations