© 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 EvalsExportsAPI 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. 26100
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    42
    +0.13
    0.7%
    26
    +0.10
    0.6%
    206
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    291
    +0.13
    0.00
    384
    +0.10
    0.00
    167
    +0.10
    0.00
    Negative Logits
    £
    -1.76
    ²
    -1.68
    erals
    -1.61
    ľĵ
    -1.55
    ĻĤ
    -1.50
    ķ
    -1.46
    ¨
    -1.46
    estock
    -1.45
     interloc
    -1.40
     caption
    -1.39
    POSITIVE LOGITS
    ureus
    2.06
    ?”
    1.53
    "?
    1.48
    ioned
    1.47
    uber
    1.44
    '?"
    1.43
    rior
    1.39
    ulp
    1.37
    ort
    1.36
    '?
    1.35
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.