© 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. 2-RES-SM
    11. 12700
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to data analysis and outcomes

    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
    186
    +0.25
    1.5%
    153
    +0.24
    1.5%
    68
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.25
    0.10
    186
    +0.24
    0.07
    400
    +0.14
    0.05
    Negative Logits
    http
    -1.55
     overlooking
    -1.55
    blogger
    -1.51
     http
    -1.41
     Judges
    -1.39
     interviewing
    -1.39
    gels
    -1.35
    ferencing
    -1.34
     scaff
    -1.34
     exclusively
    -1.31
    POSITIVE LOGITS
    ĻĤ
    3.75
    £
    2.98
    Ļª
    2.87
    ľ
    2.80
    »
    2.75
    Ĥ¬
    2.74
    Ĺ
    2.72
    ĥ½
    2.72
    »¿
    2.70
    ĩ
    2.69
    Activations Density 3.473%

    No Known Activations