© 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. 2-RES-SM
    11. 27528
    Prev
    Next
    INDEX
    Explanations

    references to sameness or identical characteristics

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    436
    +0.14
    0.8%
    403
    +0.14
    0.8%
    94
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    94
    +0.14
    0.04
    403
    +0.14
    0.04
    318
    +0.13
    0.03
    Negative Logits
    reduc
    -1.71
    kan
    -1.66
    abad
    -1.58
    oux
    -1.49
    "]
    -1.46
    lessness
    -1.44
    orus
    -1.43
    ERE
    -1.42
    bys
    -1.41
    ADE
    -1.40
    POSITIVE LOGITS
     thing
    2.22
     across
    1.79
    ?).
    1.75
    iator
    1.71
     applies
    1.70
    áĢº
    1.62
     sized
    1.62
     goes
    1.61
    iates
    1.54
     kind
    1.52
    Activations Density 0.099%

    No Known Activations