© 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. 25922
    Prev
    Next
    INDEX
    Explanations

    conditions related to compliance and requirements in legal or formal documents

    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
    148
    +0.14
    0.8%
    463
    +0.13
    0.7%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    463
    +0.14
    0.03
    462
    +0.13
    0.02
    233
    +0.12
    0.02
    Negative Logits
    >&
    -1.66
    hip
    -1.57
    ffected
    -1.55
    makers
    -1.55
    employed
    -1.47
    »¿
    -1.46
    cause
    -1.44
    built
    -1.42
    grown
    -1.41
    SON
    -1.41
    POSITIVE LOGITS
    iculously
    2.64
    ropol
    2.21
    iculous
    2.19
    tle
    1.74
    ropolis
    1.67
     nex
    1.60
    formin
    1.56
    rically
    1.55
    zes
    1.49
     anytime
    1.47
    Activations Density 0.052%

    No Known Activations