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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 26786
    Prev
    Next
    INDEX
    Explanations

    references to data and its significance in various contexts

    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
    470
    +0.18
    1.0%
    23
    +0.12
    0.7%
    228
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    361
    +0.18
    0.06
    287
    +0.12
    0.05
    293
    +0.12
    0.04
    Negative Logits
    able
    -1.75
    "}](#
    -1.73
    lining
    -1.70
    lined
    -1.63
    bound
    -1.58
    BOX
    -1.58
    ahead
    -1.58
    sible
    -1.53
    boxes
    -1.41
    chains
    -1.41
    POSITIVE LOGITS
    ĻĤ
    1.82
    arly
    1.68
    ammar
    1.51
     School
    1.49
    rae
    1.49
    ophila
    1.45
    yses
    1.45
    ose
    1.44
    viously
    1.41
    icer
    1.40
    Activations Density 0.033%

    No Known Activations