© 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. 4-RES-SM
    11. 14979
    Prev
    Next
    INDEX
    Explanations

    expressions of personal feelings and emotional states

    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
    156
    +0.15
    0.9%
    378
    +0.15
    0.8%
    417
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    378
    +0.15
    0.11
    149
    +0.15
    0.10
    263
    +0.12
    0.12
    Negative Logits
     ↵
    -5.40
    -5.40
     ↵
    -5.40
    -5.40
    -5.40
    <|outofrange|>
    -5.40
    <|outofrange|>
    -5.40
    č↵
    -5.40
    -5.40
    -5.40
    POSITIVE LOGITS
    ently
    2.38
    ly
    2.33
    ably
    2.32
     tremend
    2.30
    ively
    2.27
     immensely
    2.27
    edly
    2.22
    atically
    2.20
    fully
    2.18
    estly
    2.14
    Activations Density 1.637%

    No Known Activations