© 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. 11205
    Prev
    Next
    INDEX
    Explanations

    specific product or brand names

    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
    21
    +0.32
    2.1%
    331
    +0.12
    0.8%
    231
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.32
    0.10
    255
    +0.12
    0.00
    450
    +0.09
    0.03
    Negative Logits
    alties
    -1.34
     estimating
    -1.29
    thon
    -1.26
    vere
    -1.24
     repe
    -1.14
     recom
    -1.13
     forecast
    -1.12
     hall
    -1.12
    dorff
    -1.11
     elev
    -1.10
    POSITIVE LOGITS
    ¯
    2.33
    Ĺ
    2.31
    ³
    2.20
    µ
    2.13
    ²
    2.10
    ´
    2.04
    ®
    2.02
    °
    2.02
    ir
    2.01
    ¤
    1.99
    Activations Density 0.791%

    No Known Activations