© 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. 0-MLP-SM
    11. 27742
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions and the concept of absence or deficiency

    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
    164
    +0.15
    0.9%
    115
    +0.14
    0.8%
    499
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    426
    +0.15
    0.01
    499
    +0.14
    0.01
    39
    +0.11
    0.01
    Negative Logits
    MOESM
    -1.75
     Respondents
    -1.63
    aning
    -1.58
    llll
    -1.57
    ·
    -1.54
     vain
    -1.52
    TY
    -1.49
     others
    -1.46
    aco
    -1.45
    aved
    -1.45
    POSITIVE LOGITS
    imization
    1.84
    caster
    1.83
    pective
    1.75
     permits
    1.71
    casters
    1.68
     mechanism
    1.66
    gap
    1.60
    imum
    1.60
     identifier
    1.59
     contender
    1.58
    Activations Density 0.018%

    No Known Activations