© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 27149
    Prev
    Next
    INDEX
    Explanations

    HTML or XML tags and structure

    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
    383
    +0.13
    0.8%
    17
    +0.12
    0.7%
    37
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    327
    +0.13
    0.08
    240
    +0.12
    0.01
    37
    +0.12
    0.07
    Negative Logits
    ĻĤ
    -3.78
    £
    -3.73
    Ļ
    -3.31
    ħ
    -3.22
    ³
    -3.21
    ¶
    -3.21
    Ł
    -3.20
    Ĥ¬
    -3.15
    ¼
    -3.14
    Ħ
    -3.09
    POSITIVE LOGITS
    ferences
    2.01
    zione
    1.67
    ference
    1.57
    igm
    1.55
    theless
    1.51
    figure
    1.50
    llo
    1.50
    ematic
    1.49
    jection
    1.49
    fficients
    1.47
    Activations Density 1.181%

    No Known Activations