© 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. 26340
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "git" and its variations

    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
    156
    +0.21
    1.2%
    410
    +0.14
    0.8%
    369
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.21
    0.01
    321
    +0.14
    0.02
    335
    +0.13
    0.01
    Negative Logits
    ´
    -1.65
     cystic
    -1.51
    igm
    -1.49
    ospital
    -1.47
    uscular
    -1.44
    ises
    -1.41
    onna
    -1.40
     tumour
    -1.40
     bother
    -1.38
    atern
    -1.37
    POSITIVE LOGITS
    ://
    1.67
    Hub
    1.60
     origin
    1.57
    Sprintf
    1.51
    rification
    1.39
    oppel
    1.34
    eln
    1.33
    beans
    1.32
     Instr
    1.30
    etting
    1.30
    Activations Density 0.107%

    No Known Activations