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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 29000
    Prev
    Next
    INDEX
    Explanations

    instances of the word "until."

    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
    +0.14
    0.8%
    292
    +0.13
    0.7%
    193
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    292
    +0.14
    0.04
    193
    +0.13
    0.04
    404
    +0.12
    0.04
    Negative Logits
    helm
    -1.75
    keit
    -1.74
    ¢
    -1.53
    th
    -1.50
    STEM
    -1.43
     shoes
    -1.40
    ister
    -1.40
    gly
    -1.39
    kin
    -1.37
     alike
    -1.35
    POSITIVE LOGITS
    ahoma
    1.66
    ndef
    1.48
    iful
    1.48
     elimination
    1.45
     midnight
    1.44
     completion
    1.41
    iday
    1.39
     elif
    1.39
     date
    1.39
     else
    1.38
    Activations Density 0.194%

    No Known Activations