© 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. 26020
    Prev
    Next
    INDEX
    Explanations

    instances of spelling and grammatical errors

    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
    58
    +0.12
    0.7%
    376
    +0.12
    0.7%
    503
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.12
    0.01
    258
    +0.12
    0.02
    203
    +0.12
    0.02
    Negative Logits
    §
    -3.24
    Ŀ
    -3.08
    ķ
    -3.08
    ½
    -3.05
    ¬
    -2.96
    ĥ½
    -2.93
    ↵↵
    -2.83
    ↵
    -2.83
    -2.82
     ↵
    -2.82
    POSITIVE LOGITS
    ulator
    1.69
    scriptsize
    1.69
    sheet
    1.68
    caster
    1.67
    hors
    1.63
    works
    1.59
    istry
    1.56
    ,[
    1.56
    staff
    1.55
    smen
    1.53
    Activations Density 3.571%

    No Known Activations