© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10824
    Prev
    Next
    INDEX
    Explanations

    references to specific values or metrics that signify changes or results in a context-related discussion

    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
    98
    +0.22
    1.3%
    478
    +0.19
    1.1%
    291
    +0.18
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    291
    +0.22
    0.20
    10
    +0.19
    0.16
    98
    +0.18
    0.04
    Negative Logits
    "}](#
    -2.28
    ius
    -1.72
     caps
    -1.41
    cule
    -1.40
    ipro
    -1.35
     chromatography
    -1.31
     hur
    -1.30
    pieces
    -1.30
     aliqu
    -1.30
    ieties
    -1.29
    POSITIVE LOGITS
     latter
    2.38
     same
    2.16
     aforementioned
    2.16
    rapeut
    1.88
     usual
    1.87
    same
    1.77
    oretic
    1.74
     likes
    1.73
     following
    1.72
     latest
    1.72
    Activations Density 1.633%

    No Known Activations