Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 29668
    Prev
    Next
    INDEX
    Explanations

    information related to inventions or technical devices

    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
    478
    +0.12
    0.6%
    159
    +0.11
    0.6%
    270
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    407
    +0.12
    0.02
    403
    +0.11
    0.02
    418
    +0.10
    -0.00
    Negative Logits
    orian
    -1.59
    argin
    -1.47
     analyzer
    -1.44
     taps
    -1.42
     spectrometer
    -1.36
     degrees
    -1.35
    pid
    -1.33
    urn
    -1.31
    was
    -1.30
    ORT
    -1.28
    POSITIVE LOGITS
    having
    1.71
     heretofore
    1.65
     embodiments
    1.53
     disadvantage
    1.41
     presently
    1.41
     said
    1.40
     existing
    1.39
    said
    1.39
    icularly
    1.36
    above
    1.34
    Activations Density 0.118%

    No Known Activations