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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 25484
    Prev
    Next
    INDEX
    Explanations

    the concept of "blast," indicating a focus on explosive or powerful events or themes

    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
    376
    +0.11
    0.6%
    43
    +0.11
    0.6%
    286
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.11
    0.02
    203
    +0.11
    0.02
    56
    +0.10
    0.00
    Negative Logits
    ĥ½
    -2.37
    ľĵ
    -2.25
    ı
    -2.12
    ĨĴ
    -2.10
    ¿½
    -2.07
    ¯
    -2.04
    ľ
    -1.99
    ²
    -1.95
    Ķ
    -1.95
    ¥
    -1.93
    POSITIVE LOGITS
    assic
    1.71
    iative
    1.65
    ongs
    1.62
     defeats
    1.58
    idium
    1.55
    ición
    1.54
     escapes
    1.53
    mann
    1.52
    kill
    1.52
    mans
    1.50
    Activations Density 4.403%

    No Known Activations