© 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. 29692
    Prev
    Next
    INDEX
    Explanations

    instances of the letter 'b' in various forms, indicating a focus on words that start or contain 'b'

    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
    43
    +0.13
    0.7%
    33
    +0.12
    0.7%
    28
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.13
    0.00
    377
    +0.12
    0.00
    373
    +0.12
    0.00
    Negative Logits
    ĨĴ
    -2.50
    Ļª
    -2.18
    »¿
    -1.87
    ¬
    -1.51
     louder
    -1.51
    ĥ
    -1.49
    ¯
    -1.46
     occasional
    -1.43
    /~
    -1.40
    ¾
    -1.39
    POSITIVE LOGITS
    ullah
    1.58
    \])]{}
    1.55
    ocol
    1.54
    opol
    1.52
    cf
    1.52
    ouri
    1.47
    rived
    1.47
    ocre
    1.46
    ochond
    1.45
    onsieur
    1.43
    Activations Density 0.000%

    No Known Activations