© 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. 2-RES-SM
    11. 9839
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Sh."

    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
    369
    +0.24
    1.4%
    59
    +0.14
    0.8%
    173
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    173
    +0.24
    0.03
    369
    +0.14
    0.02
    477
    +0.13
    0.04
    Negative Logits
    lique
    -1.81
    icip
    -1.75
    estion
    -1.73
    etically
    -1.70
    ese
    -1.65
    ocl
    -1.60
    cludes
    -1.59
    ency
    -1.58
    ternal
    -1.57
    icos
    -1.55
    POSITIVE LOGITS
    apiro
    1.63
    akespeare
    1.58
    outs
    1.53
    uffle
    1.52
    adows
    1.44
    baz
    1.44
    rimp
    1.40
    cock
    1.40
    waves
    1.39
    rooms
    1.39
    Activations Density 0.152%

    No Known Activations