© 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. 4-RES-SM
    11. 10058
    Prev
    Next
    INDEX
    Explanations

    embedded codes or scripts within the 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/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
    255
    +0.18
    1.0%
    103
    +0.15
    0.9%
    21
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    128
    +0.18
    0.03
    255
    +0.15
    0.01
    138
    +0.14
    0.04
    Negative Logits
    doms
    -1.94
    ’
    -1.42
     himself
    -1.42
    ?”
    -1.40
    .”).
    -1.36
    .")
    -1.35
    .").
    -1.35
    s
    -1.35
    )\]
    -1.34
    selves
    -1.33
    POSITIVE LOGITS
    į
    3.48
    ı
    3.19
    ¥
    3.18
    ģ
    3.13
    >{{
    3.07
    >-
    3.03
    £
    3.02
    ><
    3.02
    >
    2.98
    ¬
    2.98
    Activations Density 0.107%

    No Known Activations