© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 27902
    Prev
    Next
    INDEX
    Explanations

    statistical data and numerical metrics related to studies or research findings

    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
    203
    +0.14
    0.7%
    271
    +0.14
    0.7%
    391
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.14
    0.06
    136
    +0.14
    -0.01
    391
    +0.12
    0.04
    Negative Logits
    .";
    -1.71
    ↵	↵
    -1.70
    :`
    -1.63
    """
    -1.53
    ings
    -1.47
    ↵↵↵↵↵
    -1.46
    apters
    -1.43
    itions
    -1.43
    schemas
    -1.40
    tons
    -1.39
    POSITIVE LOGITS
     %)
    1.83
    ))^
    1.80
     ),
    1.66
     )\
    1.60
    )^
    1.58
    )'
    1.58
    disambiguation
    1.57
    )/\
    1.54
    +)
    1.53
    ^),
    1.52
    Activations Density 0.473%

    No Known Activations