© 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. 24595
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences or subjective viewpoints

    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
    23
    +0.27
    1.5%
    126
    +0.15
    0.9%
    1
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.27
    0.12
    126
    +0.15
    0.08
    488
    +0.14
    0.07
    Negative Logits
     myself
    -1.43
     Cookies
    -1.42
    ного
    -1.41
     themselves
    -1.40
     Err
    -1.37
    bee
    -1.36
     Himself
    -1.35
    ettes
    -1.34
     album
    -1.32
    weg
    -1.32
    POSITIVE LOGITS
    rapy
    1.64
    rapeutics
    1.53
    oming
    1.52
     pronounced
    1.48
     preponderance
    1.47
    oretical
    1.45
    tering
    1.45
    ights
    1.44
    )));
    1.40
    disambiguation
    1.39
    Activations Density 1.463%

    No Known Activations