© 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. 29374
    Prev
    Next
    INDEX
    Explanations

    references to being impacted or influenced by various factors or events

    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
    268
    +0.17
    1.0%
    277
    +0.14
    0.8%
    156
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    268
    +0.17
    0.03
    277
    +0.14
    0.02
    315
    +0.13
    0.02
    Negative Logits
    Īĺ
    -1.73
    heed
    -1.51
    starter
    -1.50
    uther
    -1.47
    eval
    -1.46
    »¿
    -1.44
    ille
    -1.43
    ethanol
    -1.42
     educated
    -1.39
    µ
    -1.37
    POSITIVE LOGITS
    uar
    1.62
     slopes
    1.56
    **:
    1.48
     households
    1.46
     sectors
    1.42
    hang
    1.42
    ?:
    1.41
     zones
    1.39
     affecting
    1.39
     compartments
    1.37
    Activations Density 0.079%

    No Known Activations