© 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. 1-RES-SM
    11. 24412
    Prev
    Next
    INDEX
    Explanations

    sections labeled as "Description" or "Details" in a text

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    461
    +0.12
    0.7%
    58
    +0.12
    0.6%
    464
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    464
    +0.12
    0.01
    390
    +0.12
    0.01
    365
    +0.12
    0.01
    Negative Logits
     visitor
    -1.56
    %).
    -1.52
    aps
    -1.51
     others
    -1.44
    twitter
    -1.44
    prison
    -1.43
    mun
    -1.41
    place
    -1.39
    än
    -1.37
    others
    -1.37
    POSITIVE LOGITS
    igned
    1.59
     Period
    1.56
     Playing
    1.53
     Examples
    1.52
    ³
    1.48
    ographically
    1.45
    etto
    1.45
    ovo
    1.43
     Ampl
    1.41
    atory
    1.40
    Activations Density 0.026%

    No Known Activations