© 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. 8960
    Prev
    Next
    INDEX
    Explanations

    expressions of community involvement and collaboration

    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
    348
    +0.18
    1.0%
    78
    +0.13
    0.7%
    281
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.18
    0.05
    281
    +0.13
    0.10
    392
    +0.12
    0.04
    Negative Logits
    »¿
    -2.35
    ĻĤ
    -2.33
    ĸ´
    -1.79
    Ĺ
    -1.78
    Ł
    -1.76
    «
    -1.72
    ¡
    -1.70
    ¶
    -1.70
    ł
    -1.69
    Ī
    -1.67
    POSITIVE LOGITS
     mentor
    2.55
     nurt
    2.51
     leadership
    2.44
     empower
    2.37
     educ
    2.36
     ment
    2.34
     collabor
    2.32
     innov
    2.32
     expertise
    2.27
     ethic
    2.25
    Activations Density 3.041%

    No Known Activations