© 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. 1-RES-SM
    11. 24755
    Prev
    Next
    INDEX
    Explanations

    terms related to health care and industry

    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
    111
    +0.15
    0.9%
    129
    +0.11
    0.6%
    484
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    275
    +0.15
    0.10
    376
    +0.11
    0.03
    286
    +0.11
    0.07
    Negative Logits
    sson
    -1.74
    ...](
    -1.69
    harma
    -1.68
    compat
    -1.54
    abbath
    -1.50
    fections
    -1.47
    ARRANT
    -1.42
    aliana
    -1.41
    ttes
    -1.41
    **:
    -1.36
    POSITIVE LOGITS
    ĻĤ
    3.91
    ´
    3.81
    ¿½
    3.78
    °
    3.78
    ®
    3.53
    ¾
    3.53
    ¦
    3.50
    «
    3.42
    č↵
    3.42
       ↵
    3.42
    Activations Density 1.849%

    No Known Activations