© 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. 2-RES-SM
    11. 31896
    Prev
    Next
    INDEX
    Explanations

    corporate-related terms and organizational structures

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    419
    +0.21
    1.2%
    271
    +0.19
    1.1%
    47
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.21
    0.07
    419
    +0.19
    0.06
    271
    +0.13
    0.01
    Negative Logits
     wont
    -1.51
     previous
    -1.42
    cludes
    -1.37
     anc
    -1.35
     accord
    -1.35
     msgid
    -1.33
     awaited
    -1.33
     principle
    -1.30
     session
    -1.30
     pend
    -1.29
    POSITIVE LOGITS
    İ
    1.84
     albicans
    1.82
     herself
    1.70
    bery
    1.70
    »
    1.65
     himself
    1.63
    ĩ
    1.62
    ии
    1.61
    §
    1.60
    ¦
    1.54
    Activations Density 0.502%

    No Known Activations