Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27533
    Prev
    Next
    INDEX
    Explanations

    file extensions or wildcard patterns

    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
    23
    +0.25
    1.4%
    478
    +0.16
    0.9%
    156
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    504
    +0.25
    0.01
    258
    +0.16
    0.01
    510
    +0.14
    0.01
    Negative Logits
    ·
    -1.98
    «
    -1.79
    Äį
    -1.75
    Ļ
    -1.74
    boats
    -1.70
    cad
    -1.65
    =”
    -1.62
    Ľ
    -1.59
    µ
    -1.56
     analyzer
    -1.56
    POSITIVE LOGITS
    rapeutic
    1.75
    selves
    1.65
     sudden
    1.56
    tgz
    1.52
     new
    1.49
    leans
    1.47
    perate
    1.46
    comes
    1.46
     flesh
    1.44
     Protestant
    1.44
    Activations Density 0.006%

    No Known Activations