© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 12136
    Prev
    Next
    INDEX
    Explanations

    references to figures and diagrams in a document

    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
    21
    +0.15
    0.8%
    78
    +0.12
    0.7%
    75
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    3
    +0.15
    0.01
    248
    +0.12
    0.01
    395
    +0.12
    0.01
    Negative Logits
    ships
    -1.63
    than
    -1.59
    ()->
    -1.55
    gery
    -1.51
    ments
    -1.44
     prescriptions
    -1.43
    bery
    -1.42
    abases
    -1.40
    irth
    -1.36
    ing
    -1.35
    POSITIVE LOGITS
    Ĭ
    3.71
    ©
    3.55
    ŀ
    3.13
    ĩ
    3.10
    ±
    3.07
    Ĥ
    3.05
    İ
    3.04
    Ķ
    3.03
    Ī
    3.02
    ¡
    3.01
    Activations Density 0.045%

    No Known Activations