© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 28553
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    489
    +0.14
    0.8%
    136
    +0.12
    0.7%
    152
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.14
    0.00
    1
    -0.12
    0.00
    2
    -0.11
    0.00
    Negative Logits
    ĺ
    -2.76
    Ļª
    -2.71
    ĭ
    -2.66
    ħ
    -2.54
    ¢
    -2.54
    ĻĤ
    -2.49
    ĩ
    -2.48
    Ĵ
    -2.42
    ĵ
    -2.40
    ĥ
    -2.38
    POSITIVE LOGITS
    SEA
    1.55
     oversight
    1.52
    ********************************
    1.52
    GPL
    1.52
    elon
    1.50
    ielder
    1.49
    lish
    1.48
    slash
    1.44
    ****************************************************************************
    1.43
    --"
    1.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.