© 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. 29326
    Prev
    Next
    INDEX
    Explanations

    references to locations in the context of cultural or historical discussions

    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
    101
    +0.14
    0.8%
    5
    +0.13
    0.8%
    388
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    101
    +0.14
    0.03
    258
    +0.13
    0.02
    40
    +0.12
    0.03
    Negative Logits
    middle
    -1.44
     .=
    -1.44
     alt
    -1.43
     value
    -1.43
     middle
    -1.41
     equal
    -1.41
    ).$
    -1.37
     )$
    -1.37
     time
    -1.36
    }.$
    -1.35
    POSITIVE LOGITS
    pora
    1.73
    uscript
    1.73
    illac
    1.70
    SON
    1.68
    vier
    1.64
    uary
    1.63
    oque
    1.62
    ient
    1.58
    ename
    1.57
    vell
    1.56
    Activations Density 0.230%

    No Known Activations