© 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. 2-RES-SM
    11. 12859
    Prev
    Next
    INDEX
    Explanations

    Java class and interface definitions

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    +0.15
    0.8%
    148
    +0.13
    0.7%
    431
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    350
    +0.15
    0.03
    431
    +0.13
    0.02
    17
    +0.12
    0.01
    Negative Logits
    ĻĤ
    -2.44
    ´
    -2.22
    ½
    -2.17
    ļ
    -2.14
    ·¸
    -2.12
    ľĵ
    -2.10
    ĥ
    -2.03
    ³
    -1.99
    cca
    -1.96
    ľ
    -1.95
    POSITIVE LOGITS
    ified
    1.95
    ific
    1.73
    ify
    1.66
    istics
    1.65
    ification
    1.64
    iorari
    1.60
    ical
    1.60
    isms
    1.58
    ics
    1.56
    FromString
    1.56
    Activations Density 0.194%

    No Known Activations