© 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. 4-RES-SM
    11. 9538
    Prev
    Next
    INDEX
    Explanations

    chemical compound names and their variations

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    21
    +0.14
    0.8%
    2
    +0.13
    0.7%
    306
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    448
    +0.14
    0.01
    2
    +0.13
    0.01
    287
    +0.13
    0.01
    Negative Logits
     forth
    -1.70
    ockets
    -1.65
    forth
    -1.62
    rely
    -1.57
    ician
    -1.55
    osus
    -1.55
    ivas
    -1.52
    rology
    -1.48
    ://
    -1.47
    NER
    -1.44
    POSITIVE LOGITS
    °
    2.50
    §
    2.50
    ij
    2.50
    ĥ
    2.38
    İ
    2.28
    ħ
    2.28
    sulf
    2.17
     ester
    2.16
    ¸
    2.15
    Ģ
    2.13
    Activations Density 0.021%

    No Known Activations