© 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. 26371
    Prev
    Next
    INDEX
    Explanations

    references to actions or concepts that are explicitly described or emphasized

    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
    393
    +0.16
    0.9%
    466
    +0.13
    0.7%
    155
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.16
    0.22
    185
    +0.13
    0.18
    165
    +0.12
    0.17
    Negative Logits
    vent
    -1.63
     forth
    -1.56
    ]--
    -1.52
     Brotherhood
    -1.39
    player
    -1.35
     strict
    -1.33
     weeks
    -1.30
    omen
    -1.29
    istant
    -1.28
    igate
    -1.28
    POSITIVE LOGITS
    quito
    1.53
     Laboratories
    1.53
     METHODS
    1.50
    ĻĤ
    1.47
    ickers
    1.45
    ¹
    1.45
    borough
    1.41
    es
    1.39
    İ
    1.39
    aux
    1.38
    Activations Density 0.393%

    No Known Activations