© 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. 25315
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and conditions

    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
    431
    +0.12
    0.7%
    172
    +0.11
    0.6%
    502
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    431
    +0.12
    0.02
    172
    +0.11
    0.01
    54
    +0.10
    0.02
    Negative Logits
    ½
    -2.11
    Ń
    -1.86
    ľĵ
    -1.84
    »
    -1.83
    §
    -1.82
    ´
    -1.68
    brains
    -1.67
    »¿
    -1.67
    ¿½
    -1.66
    '):
    -1.63
    POSITIVE LOGITS
    ending
    1.58
    helf
    1.49
    iem
    1.46
    ymphony
    1.45
     of
    1.44
     "-
    1.42
    creen
    1.37
    ynthesis
    1.36
    cloth
    1.33
    ensory
    1.33
    Activations Density 0.037%

    No Known Activations