© 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. 2-RES-SM
    11. 27206
    Prev
    Next
    INDEX
    Explanations

    elements related to storytelling and narrative descriptions

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    156
    +0.21
    1.2%
    263
    +0.19
    1.1%
    153
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    76
    +0.21
    0.10
    382
    +0.19
    0.10
    297
    +0.15
    0.12
    Negative Logits
     yours
    -1.66
     ours
    -1.60
    ETHOD
    -1.45
    orship
    -1.38
    ITT
    -1.37
     ahead
    -1.35
    icity
    -1.35
    OLOG
    -1.34
     theirs
    -1.34
    sec
    -1.31
    POSITIVE LOGITS
    strand
    1.38
     portions
    1.35
     Present
    1.32
    ĸ´
    1.30
     edition
    1.27
     boxes
    1.26
    lied
    1.25
     Tap
    1.24
     reel
    1.24
    iella
    1.23
    Activations Density 4.281%

    No Known Activations