© 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. 29834
    Prev
    Next
    INDEX
    Explanations

    assertions of belief or conviction

    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
    115
    +0.16
    0.9%
    376
    +0.15
    0.8%
    22
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    22
    +0.16
    0.02
    31
    +0.15
    0.02
    462
    +0.12
    0.02
    Negative Logits
    ainen
    -1.99
    chle
    -1.65
    sein
    -1.63
    porter
    -1.57
    osen
    -1.54
    ce
    -1.49
    eller
    -1.48
    ello
    -1.48
    kat
    -1.46
    erk
    -1.46
    POSITIVE LOGITS
    Īĺ
    1.74
    İ
    1.68
    Ĥ¬
    1.64
    idden
    1.50
    safe
    1.50
     unity
    1.49
    ¦
    1.44
     satisfactory
    1.44
    locked
    1.43
     insufficient
    1.43
    Activations Density 1.825%

    No Known Activations