© 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. 28834
    Prev
    Next
    INDEX
    Explanations

    terms related to textures and their properties in digital graphics

    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
    156
    +0.23
    1.3%
    392
    +0.14
    0.8%
    173
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.23
    0.03
    152
    +0.14
    0.03
    173
    +0.14
    0.02
    Negative Logits
    ureus
    -1.67
    olic
    -1.52
     obese
    -1.50
     recommending
    -1.50
     congreg
    -1.49
    amais
    -1.46
    otoxin
    -1.45
    otransferase
    -1.44
    eon
    -1.44
     subscrib
    -1.43
    POSITIVE LOGITS
    MRI
    1.60
    ière
    1.59
    istry
    1.54
    CHA
    1.51
    istor
    1.49
    maker
    1.48
    \])]{}
    1.45
    ERTY
    1.44
    ontal
    1.43
    BUFFER
    1.41
    Activations Density 0.181%

    No Known Activations