© 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. 2-RES-SM
    11. 27650
    Prev
    Next
    INDEX
    Explanations

    JSON object structures and key-value pairs

    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
    192
    +0.12
    0.6%
    67
    +0.11
    0.6%
    119
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.12
    0.09
    119
    +0.11
    0.08
    450
    +0.10
    0.09
    Negative Logits
    ()</
    -1.58
    respectively
    -1.52
    etimes
    -1.44
    phal
    -1.43
    npmjs
    -1.42
    .’
    -1.41
    upon
    -1.40
    ”.
    -1.38
     lately
    -1.37
    ’.
    -1.36
    POSITIVE LOGITS
    Ĥ
    2.74
    ©
    2.46
    ł
    2.44
    «
    2.43
    ķ
    2.31
    ´
    2.30
    ¸
    2.26
    ģ
    2.18
    ³
    2.17
    ¦
    2.10
    Activations Density 0.512%

    No Known Activations