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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12253
    Prev
    Next
    INDEX
    Explanations

    structured elements and HTML tags in the markup

    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
    143
    +0.16
    0.9%
    370
    +0.12
    0.7%
    93
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    370
    +0.16
    0.08
    143
    +0.12
    0.05
    206
    +0.11
    0.04
    Negative Logits
    ľĵ
    -3.68
    Ī
    -3.56
    Ļª
    -3.27
    ĥ½
    -3.25
    »¿
    -3.23
    Ĥ
    -3.23
    ¤
    -3.22
    ĻĤ
    -3.20
    ®
    -3.18
    ĩ
    -3.13
    POSITIVE LOGITS
    unction
    1.39
    icol
    1.33
    rief
    1.33
     BLOCK
    1.31
    onday
    1.28
    attachment
    1.27
     bellow
    1.26
    reet
    1.25
    row
    1.24
     snaps
    1.24
    Activations Density 0.290%

    No Known Activations