© 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. 1-RES-SM
    11. 25350
    Prev
    Next
    INDEX
    Explanations

    programming structures and components within a code or script context

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    152
    +0.14
    0.8%
    245
    +0.13
    0.8%
    165
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    245
    +0.14
    0.03
    152
    +0.13
    0.03
    165
    +0.13
    0.02
    Negative Logits
     Heights
    -1.54
    ths
    -1.52
    ymers
    -1.51
    ophilic
    -1.50
     hereto
    -1.48
    ational
    -1.47
    omes
    -1.44
    hey
    -1.44
    ophag
    -1.43
    ickets
    -1.41
    POSITIVE LOGITS
    smallcaps
    1.77
    mente
    1.55
    director
    1.55
     overhaul
    1.54
    ieurs
    1.49
     guerra
    1.47
     excuses
    1.46
     prepares
    1.45
    libc
    1.44
    anchez
    1.42
    Activations Density 0.057%

    No Known Activations