© 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 EvalsExportsAPI 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. 10887
    Prev
    Next
    INDEX
    Explanations

    references to software downloads and resource availability

    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
    307
    +0.31
    1.8%
    306
    +0.15
    0.9%
    333
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    302
    +0.31
    0.11
    315
    +0.15
    0.10
    425
    +0.15
    0.11
    Negative Logits
    isher
    -1.64
    breaker
    -1.60
    uple
    -1.59
    ester
    -1.51
    landers
    -1.50
    keit
    -1.48
     lasted
    -1.43
     quo
    -1.42
     burgl
    -1.36
    chers
    -1.35
    POSITIVE LOGITS
     http
    3.21
     www
    3.08
     https
    2.95
    ://
    2.39
    http
    2.32
    www
    2.31
     below
    2.31
     ibid
    2.30
    ±
    2.27
     page
    2.25
    Activations Density 1.531%

    No Known Activations