© 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. 25564
    Prev
    Next
    INDEX
    Explanations

    instances of the letter 's' in various contexts

    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
    369
    +0.20
    1.2%
    81
    +0.16
    0.9%
    156
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.20
    0.04
    484
    +0.16
    0.03
    32
    +0.13
    0.03
    Negative Logits
    İ
    -2.63
    ħ
    -2.51
    ĥ
    -2.50
    Ĥ
    -2.44
    ¼
    -2.34
    Ķ
    -2.29
    ı
    -2.27
    ľĵ
    -2.25
    Ĭ
    -2.24
    ¨
    -2.22
    POSITIVE LOGITS
    vens
    1.81
    ittest
    1.60
    ided
    1.58
    izing
    1.58
     called
    1.54
    hering
    1.54
    iff
    1.51
    idenote
    1.50
     written
    1.48
    noop
    1.47
    Activations Density 0.022%

    No Known Activations