© 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. 24779
    Prev
    Next
    INDEX
    Explanations

    instances of personal experiences and pronouns indicating involvement in a narrative

    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
    23
    +0.24
    1.4%
    433
    +0.13
    0.7%
    478
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    433
    +0.24
    0.05
    23
    +0.13
    0.06
    478
    +0.12
    0.01
    Negative Logits
    ”:
    -1.72
    ”?
    -1.71
    ]]>
    -1.62
    ató
    -1.60
    #,
    -1.58
    />.
    -1.58
    "><
    -1.56
    msgstr
    -1.53
    "</
    -1.52
    ”—
    -1.51
    POSITIVE LOGITS
    akov
    1.74
     ')
    1.65
     soon
    1.60
     easiest
    1.59
     me
    1.56
     ',
    1.54
     theirs
    1.53
    ^-
    1.48
     wouldn
    1.47
     confused
    1.46
    Activations Density 0.680%

    No Known Activations