© 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. 4-RES-SM
    11. 14940
    Prev
    Next
    INDEX
    Explanations

    sections related to licensing and permissions for software use

    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
    307
    +0.26
    1.5%
    348
    +0.11
    0.6%
    470
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    192
    +0.26
    0.01
    312
    +0.11
    0.04
    508
    +0.10
    0.03
    Negative Logits
    oster
    -1.64
    roke
    -1.59
    ogh
    -1.50
    aji
    -1.44
    bie
    -1.39
    ese
    -1.39
    holm
    -1.38
    ational
    -1.37
    stown
    -1.36
    ables
    -1.35
    POSITIVE LOGITS
    ½
    2.70
    ifndef
    2.69
    pragma
    2.69
    ifdef
    2.56
    ¼
    2.53
    ŀ
    2.48
    include
    2.44
    define
    2.43
    endif
    2.36
    ²
    2.34
    Activations Density 0.119%

    No Known Activations