© 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. 28844
    Prev
    Next
    INDEX
    Explanations

    references to fate and its implications in various contexts

    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
    249
    +0.13
    0.7%
    118
    +0.12
    0.7%
    389
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    38
    +0.13
    0.02
    397
    +0.12
    0.02
    46
    +0.11
    0.02
    Negative Logits
    enough
    -1.50
    trim
    -1.48
    cket
    -1.44
    istered
    -1.40
    respectively
    -1.40
    yna
    -1.37
     whole
    -1.37
    >';
    -1.36
    you
    -1.36
     Surve
    -1.35
    POSITIVE LOGITS
    ful
    2.05
     dilemma
    1.76
     spiral
    1.58
    stones
    1.55
     quo
    1.43
    plate
    1.42
    uous
    1.42
    piece
    1.42
     ens
    1.41
    ulous
    1.40
    Activations Density 0.224%

    No Known Activations