© 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. 26263
    Prev
    Next
    INDEX
    Explanations

    references to fetishes

    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
    203
    +0.12
    0.6%
    71
    +0.11
    0.6%
    360
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    360
    +0.12
    0.01
    319
    +0.11
    0.01
    289
    +0.11
    0.01
    Negative Logits
    Ļª
    -2.04
    ĨĴ
    -1.82
    CSF
    -1.50
    soever
    -1.50
    serif
    -1.49
    ONS
    -1.43
    hip
    -1.38
    compan
    -1.37
     stool
    -1.33
    ively
    -1.32
    POSITIVE LOGITS
    etable
    1.71
     pains
    1.66
    ête
    1.63
    ete
    1.49
    ulous
    1.47
    rehen
    1.44
    ettes
    1.44
     issue
    1.44
     induct
    1.44
    ocene
    1.42
    Activations Density 0.014%

    No Known Activations