© 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. 27485
    Prev
    Next
    INDEX
    Explanations

    names of organizations and associations related to various fields

    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
    507
    +0.16
    0.9%
    168
    +0.12
    0.7%
    258
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    34
    +0.16
    0.10
    168
    +0.12
    0.07
    507
    +0.11
    0.06
    Negative Logits
    ¯
    -2.42
    Ĵ
    -2.36
    Ń
    -2.31
    Ĥ
    -2.30
    ²
    -2.29
    ¬
    -2.26
    §
    -2.25
    ĨĴ
    -2.21
    Ĥ¬
    -2.19
    ©
    -2.18
    POSITIVE LOGITS
     Directors
    1.87
    fare
    1.85
    anca
    1.76
    ship
    1.76
     Authority
    1.73
     Executive
    1.71
    ships
    1.69
     Award
    1.66
     Facility
    1.65
    liance
    1.63
    Activations Density 0.693%

    No Known Activations