© 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. 25760
    Prev
    Next
    INDEX
    Explanations

    elements related to font properties and styles in text formatting

    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
    115
    +0.12
    0.7%
    197
    +0.12
    0.7%
    385
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    197
    +0.12
    0.02
    379
    +0.12
    0.02
    349
    +0.11
    0.02
    Negative Logits
    orrh
    -1.68
    ere
    -1.53
    olate
    -1.52
    agle
    -1.50
    cibly
    -1.45
    usement
    -1.45
     Solution
    -1.44
    plicate
    -1.43
    inher
    -1.40
     same
    -1.39
    POSITIVE LOGITS
    ender
    2.09
    enders
    1.92
    ettes
    1.89
    istics
    1.87
    thouse
    1.86
    ends
    1.76
    ık
    1.67
     descriptors
    1.66
    size
    1.66
    liga
    1.65
    Activations Density 0.082%

    No Known Activations