© 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. 30318
    Prev
    Next
    INDEX
    Explanations

    code structures and control flow statements

    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
    176
    +0.13
    0.7%
    128
    +0.12
    0.7%
    416
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    35
    +0.13
    0.14
    371
    +0.12
    0.15
    18
    +0.12
    0.11
    Negative Logits
     concern
    -1.52
     Parenthood
    -1.50
     Congressional
    -1.47
    lift
    -1.47
     controversy
    -1.46
    forth
    -1.44
     arrest
    -1.42
     toll
    -1.42
     ascertain
    -1.39
     debate
    -1.38
    POSITIVE LOGITS
     tolerant
    1.65
    Ĵ
    1.56
    ·
    1.46
     behaviours
    1.40
    iative
    1.39
    elijk
    1.36
    iev
    1.36
    ´
    1.35
    ide
    1.35
    ribut
    1.33
    Activations Density 0.411%

    No Known Activations