© 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. 4-RES-SM
    11. 12582
    Prev
    Next
    INDEX
    Explanations

    references to individuals' names and their actions or roles in specific 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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    306
    +0.14
    0.8%
    208
    +0.13
    0.7%
    136
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    129
    +0.14
    0.00
    221
    +0.13
    0.02
    264
    +0.11
    0.03
    Negative Logits
    agg
    -1.87
    agging
    -1.65
    ags
    -1.63
    igg
    -1.56
     AL
    -1.47
     curiam
    -1.42
     Gilbert
    -1.42
    atorial
    -1.40
    ager
    -1.38
    ays
    -1.37
    POSITIVE LOGITS
     Ne
    3.08
     Pe
    2.90
    Pe
    2.50
    Ne
    2.50
     Me
    2.45
    Me
    2.26
    pe
    2.24
    ne
    2.19
     pe
    2.16
     NE
    2.12
    Activations Density 0.684%

    No Known Activations