© 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. 24501
    Prev
    Next
    INDEX
    Explanations

    constructs related to statistical analysis and measurement

    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
    478
    +0.20
    1.1%
    248
    +0.14
    0.8%
    153
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.20
    0.03
    153
    +0.14
    0.03
    62
    +0.12
    0.02
    Negative Logits
    FROM
    -1.73
    WITH
    -1.69
    iences
    -1.57
     rights
    -1.53
    frastructure
    -1.53
    IPE
    -1.52
    ulose
    -1.44
    lectual
    -1.42
    rights
    -1.42
    ()
    -1.38
    POSITIVE LOGITS
    âĢĬ
    1.87
     statistically
    1.63
     preponderance
    1.47
     averaging
    1.46
     randomized
    1.43
    lee
    1.39
     hunted
    1.38
     examined
    1.35
    Âł
    1.34
     randomly
    1.34
    Activations Density 0.114%

    No Known Activations