© 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. 29357
    Prev
    Next
    INDEX
    Explanations

    references to actions or processes involving "checking out" or "exploring" content

    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
    +0.15
    0.8%
    135
    +0.13
    0.7%
    197
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    135
    +0.15
    0.02
    168
    +0.13
    0.02
    197
    +0.11
    0.02
    Negative Logits
    ī
    -3.82
    ĭ
    -3.70
    ĸ
    -3.53
    ĩ
    -3.47
    §
    -3.43
    Ľ
    -3.38
    Ŀ
    -3.34
    Ł
    -3.29
    ĻĤ
    -3.25
    ĵ
    -3.23
    POSITIVE LOGITS
    iners
    1.73
     completion
    1.61
    ographer
    1.58
    objects
    1.50
    createElement
    1.45
    CAST
    1.44
    lay
    1.44
     Caption
    1.43
    ographers
    1.43
    complete
    1.42
    Activations Density 0.232%

    No Known Activations