© 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 EvalsExportsAPI 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. 27618
    Prev
    Next
    INDEX
    Explanations

    references to legal parties, particularly the term "appellee."

    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
    365
    +0.15
    0.8%
    271
    +0.13
    0.7%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.15
    0.02
    330
    +0.13
    0.01
    271
    +0.12
    0.00
    Negative Logits
     footprint
    -1.63
     ago
    -1.53
    >`
    -1.50
    )."
    -1.42
    ologies
    -1.39
    >&
    -1.37
    aneous
    -1.31
     kinda
    -1.31
     reach
    -1.30
     equation
    -1.30
    POSITIVE LOGITS
    gery
    2.24
    ibr
    1.71
    cit
    1.66
    ICAN
    1.57
    otted
    1.52
    geries
    1.50
    igate
    1.48
    quel
    1.44
     Edward
    1.43
    dom
    1.42
    Activations Density 0.160%

    No Known Activations