© 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. 14056
    Prev
    Next
    INDEX
    Explanations

    instances of actions and conditions related to checking or managing statuses and settings

    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
    307
    +0.27
    1.5%
    441
    +0.11
    0.6%
    310
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    315
    +0.27
    0.06
    91
    +0.11
    0.05
    307
    +0.11
    0.07
    Negative Logits
    strom
    -1.66
    RSOS
    -1.59
    scar
    -1.56
    recht
    -1.54
    rug
    -1.54
    worth
    -1.47
    iances
    -1.44
     strengths
    -1.44
     counterparts
    -1.43
    enz
    -1.42
    POSITIVE LOGITS
     initialization
    2.22
     update
    2.21
     debugging
    2.19
     processing
    2.18
     execution
    2.17
     reload
    2.14
     loading
    2.12
     updating
    2.11
     validation
    2.10
     refresh
    2.06
    Activations Density 0.497%

    No Known Activations