© 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 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. 26395
    Prev
    Next
    INDEX
    Explanations

    terms related to biological monitoring and measurements

    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
    410
    +0.15
    0.9%
    477
    +0.15
    0.8%
    309
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.02
    271
    +0.15
    0.00
    148
    +0.13
    0.01
    Negative Logits
     certain
    -1.99
     same
    -1.82
     favorable
    -1.78
    tered
    -1.58
     recommending
    -1.58
    ters
    -1.53
     instant
    -1.49
    fulness
    -1.47
    ffect
    -1.46
     probability
    -1.45
    POSITIVE LOGITS
    antine
    2.15
    ¤
    1.91
    ette
    1.85
    olecule
    1.85
    ĻĤ
    1.82
    prints
    1.74
    agic
    1.74
    olecular
    1.69
    etal
    1.66
    orphic
    1.65
    Activations Density 0.070%

    No Known Activations