© 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. 24416
    Prev
    Next
    INDEX
    Explanations

    references to commitments or guarantees

    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
    38
    +0.14
    0.8%
    139
    +0.13
    0.7%
    217
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    38
    +0.14
    0.03
    504
    +0.13
    0.02
    139
    +0.12
    0.02
    Negative Logits
    OVE
    -1.58
    isme
    -1.53
    sie
    -1.47
    IRE
    -1.47
    /
    -1.47
     overest
    -1.46
    ois
    -1.46
    she
    -1.46
    CK
    -1.42
    seen
    -1.42
    POSITIVE LOGITS
    ful
    1.59
    ĥ
    1.57
     prob
    1.57
    gment
    1.54
    fully
    1.51
    lessly
    1.49
    Ĺ
    1.47
     FALSE
    1.44
    gn
    1.44
    Ķ
    1.36
    Activations Density 0.170%

    No Known Activations