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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 26445
    Prev
    Next
    INDEX
    Explanations

    references to testing and assessment procedures

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    362
    +0.13
    0.8%
    111
    +0.13
    0.7%
    404
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.13
    0.03
    401
    +0.13
    0.04
    362
    +0.11
    0.02
    Negative Logits
    ¤
    -1.89
    ²
    -1.76
    ¾
    -1.68
    ³
    -1.65
    ¦
    -1.63
    ħ
    -1.59
    ģ
    -1.56
    ¨
    -1.54
    arers
    -1.54
    »
    -1.51
    POSITIVE LOGITS
    elijk
    1.60
    arium
    1.57
    /~
    1.51
     affecting
    1.50
    edy
    1.41
    rapeut
    1.39
    LAND
    1.38
     pathogenesis
    1.36
    erville
    1.36
     PKC
    1.34
    Activations Density 0.287%

    No Known Activations