© 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. 29550
    Prev
    Next
    INDEX
    Explanations

    the term 'fi' and its variations, likely indicating the presence of conditionals in code

    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
    410
    +0.14
    0.8%
    82
    +0.12
    0.7%
    37
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    37
    +0.14
    0.02
    410
    +0.12
    0.02
    272
    +0.12
    0.02
    Negative Logits
    ©
    -2.66
    Īĺ
    -2.60
    ĵ
    -2.54
    ĨĴ
    -2.53
    °
    -2.43
    Ļª
    -2.27
    ¨
    -2.22
    ľ
    -2.21
    ľĵ
    -2.21
    Ĥ¬
    -2.19
    POSITIVE LOGITS
    xtures
    3.11
    xture
    2.59
    rens
    1.91
    orent
    1.82
    ests
    1.76
    olk
    1.64
    rev
    1.60
    DAC
    1.56
    ren
    1.55
    work
    1.52
    Activations Density 0.150%

    No Known Activations