© 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. 27416
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter "b" at the beginning of words or sentences

    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
    392
    +0.17
    0.9%
    76
    +0.15
    0.9%
    248
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.17
    0.01
    271
    +0.15
    0.01
    156
    +0.13
    0.01
    Negative Logits
     correct
    -1.75
    coming
    -1.67
     desired
    -1.50
    aste
    -1.48
    rd
    -1.47
     âī¤
    -1.42
     correctly
    -1.41
     percent
    -1.39
    rely
    -1.39
     wrong
    -1.38
    POSITIVE LOGITS
    ↵³³
    1.84
    vision
    1.62
    lake
    1.45
    chen
    1.44
    wart
    1.44
    jiang
    1.41
    ãĢĢãĢĢ
    1.40
    liament
    1.39
    ']);
    1.39
    nai
    1.38
    Activations Density 0.002%

    No Known Activations