© 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. Residuals
    9. 4-RES-SM
    11. 10117
    Prev
    Next
    INDEX
    Explanations

    elements related to fantasy and supernatural themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/4-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    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
    21
    +0.34
    2.2%
    156
    +0.25
    1.6%
    269
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    269
    +0.34
    0.15
    401
    +0.25
    0.04
    108
    +0.13
    0.14
    Negative Logits
    ↵↵
    -5.73
    <|outofrange|>
    -5.73
    -5.73
                ↵
    -5.73
    ↵
    -5.73
    ↵
    -5.73
    <|outofrange|>
    -5.73
          ↵
    -5.73
    -5.73
    <|outofrange|>
    -5.73
    POSITIVE LOGITS
    ,\,
    1.56
     plus
    1.56
    ;\;
    1.51
     but
    1.51
    ,\,\
    1.50
     mellitus
    1.49
     ↵
    1.47
    ;\;\
    1.43
    ;
    1.43
     or
    1.38
    Activations Density 2.703%

    No Known Activations