© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 12011
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to court cases

    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
    21
    +0.17
    1.0%
    34
    +0.15
    0.9%
    185
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    303
    +0.17
    0.02
    185
    +0.15
    0.01
    255
    +0.14
    0.00
    Negative Logits
    zza
    -1.55
    cember
    -1.54
     time
    -1.48
     balance
    -1.44
    ément
    -1.39
    ijn
    -1.33
     infinity
    -1.32
    ulum
    -1.31
    gement
    -1.30
    lement
    -1.30
    POSITIVE LOGITS
    Defendant
    2.19
    Plaintiff
    2.19
    Defendants
    2.15
    Plaintiffs
    1.99
    @"
    1.99
    whose
    1.99
     whom
    1.97
     Defendant
    1.95
     Plaintiff
    1.92
     Assistant
    1.76
    Activations Density 0.039%

    No Known Activations