© 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. 14646
    Prev
    Next
    INDEX
    Explanations

    questions related to criteria and evaluation processes

    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
    +0.23
    1.5%
    397
    +0.22
    1.5%
    30
    +0.13
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.23
    0.11
    21
    +0.22
    0.05
    151
    +0.13
    0.03
    Negative Logits
    ”).
    -1.69
    `)
    -1.67
    ”),
    -1.58
    ”,
    -1.55
    **]{},
    -1.48
    `,
    -1.48
    ”)
    -1.46
    :**]{}
    -1.44
    ”.
    -1.40
    .”).
    -1.39
    POSITIVE LOGITS
     thereof
    1.47
    lining
    1.47
    ubicin
    1.37
    nai
    1.31
    ofib
    1.28
    \]\].
    1.26
    lying
    1.23
    Competing
    1.23
    ipel
    1.19
     His
    1.19
    Activations Density 2.757%

    No Known Activations