© 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. 25573
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the abbreviation "RE", likely indicating references to reviews or releases

    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
    369
    +0.14
    0.8%
    410
    +0.13
    0.7%
    125
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.14
    0.01
    0
    +0.13
    0.02
    410
    +0.12
    0.02
    Negative Logits
    eness
    -1.53
    opause
    -1.53
    ronic
    -1.52
    optera
    -1.47
    ono
    -1.46
    anni
    -1.43
    chitz
    -1.42
    keit
    -1.40
    abases
    -1.38
    otomy
    -1.38
    POSITIVE LOGITS
    UTERS
    1.67
    LEASE
    1.62
     inspect
    1.60
    bels
    1.44
    iator
    1.42
    PF
    1.42
    JECT
    1.41
    PORT
    1.40
    TAIN
    1.39
    verts
    1.39
    Activations Density 0.077%

    No Known Activations