© 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. 25496
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or identifiers related to data points

    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
    71
    +0.13
    0.7%
    111
    +0.13
    0.7%
    2
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.13
    0.03
    171
    +0.13
    0.02
    40
    +0.11
    0.02
    Negative Logits
    ircraft
    -1.50
    tail
    -1.44
    unnumbered
    -1.44
    ENTER
    -1.43
    dots
    -1.39
    ABILITY
    -1.38
    ferencing
    -1.33
    jections
    -1.32
     floated
    -1.32
    hes
    -1.31
    POSITIVE LOGITS
    ek
    1.59
    kowski
    1.55
    kow
    1.50
    liche
    1.49
    ung
    1.44
    nement
    1.43
    bian
    1.41
    ük
    1.41
    dz
    1.41
     password
    1.40
    Activations Density 0.102%

    No Known Activations