© 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. 29624
    Prev
    Next
    INDEX
    Explanations

    references to obstacles or restrictions

    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
    111
    +0.13
    0.7%
    191
    +0.10
    0.5%
    115
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.13
    0.02
    420
    +0.10
    0.01
    370
    +0.10
    0.01
    Negative Logits
     toxin
    -1.49
    ching
    -1.46
    fection
    -1.44
    hes
    -1.43
     latter
    -1.43
    quin
    -1.40
    ck
    -1.40
     brilliant
    -1.36
    zo
    -1.35
     confidential
    -1.35
    POSITIVE LOGITS
    ailed
    2.03
    edly
    2.03
    rance
    2.02
    ered
    1.86
    endas
    1.82
    erals
    1.74
    ivat
    1.74
    rä
    1.73
    emis
    1.71
    iom
    1.65
    Activations Density 0.229%

    No Known Activations