© 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. 1-RES-SM
    11. 28711
    Prev
    Next
    INDEX
    Explanations

    conclusive statements or logical connectors that indicate cause-and-effect relationships

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    23
    +0.23
    1.3%
    189
    +0.14
    0.8%
    402
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.23
    0.02
    404
    +0.14
    0.03
    402
    +0.12
    0.02
    Negative Logits
    ħ
    -2.55
    ĭ
    -2.53
    ļ
    -2.41
    Ĥ¬
    -2.40
    ±
    -2.33
    ĨĴ
    -2.27
    ĩ
    -2.19
    Ļª
    -2.16
    ĻĤ
    -2.15
    »¿
    -2.13
    POSITIVE LOGITS
    forth
    2.53
    ytt
    1.73
    born
    1.51
    fered
    1.49
    arily
    1.49
    cluding
    1.49
    far
    1.47
    forward
    1.46
     ')
    1.46
     delaying
    1.43
    Activations Density 0.070%

    No Known Activations