© 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. 27130
    Prev
    Next
    INDEX
    Explanations

    specific car model names and related details

    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
    28
    +0.13
    0.8%
    482
    +0.11
    0.7%
    233
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    28
    +0.13
    0.08
    233
    +0.11
    0.10
    369
    +0.11
    0.06
    Negative Logits
    ilst
    -1.51
    oxic
    -1.49
    minimal
    -1.46
     *
    -1.45
    ľĵ
    -1.43
    ĻĤ
    -1.40
    mozilla
    -1.38
     curative
    -1.35
    idopsis
    -1.34
    unden
    -1.33
    POSITIVE LOGITS
    nier
    1.89
    ?_
    1.87
    naire
    1.85
     itself
    1.82
    ño
    1.82
    "?
    1.80
     oneself
    1.76
    ”?
    1.71
     emerges
    1.69
    ifacts
    1.67
    Activations Density 1.268%

    No Known Activations