Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 26741
    Prev
    Next
    INDEX
    Explanations

    references to court cases and legal proceedings

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    111
    +0.11
    0.6%
    271
    +0.10
    0.6%
    134
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    425
    +0.11
    0.05
    331
    +0.10
    0.04
    12
    +0.10
    0.02
    Negative Logits
    ---|---|---
    -1.58
     streak
    -1.55
    obs
    -1.52
    hes
    -1.51
    Finish
    -1.50
    loss
    -1.50
    ---|---
    -1.48
     (**
    -1.47
     Obs
    -1.44
     RAW
    -1.43
    POSITIVE LOGITS
    º
    2.29
    ://
    2.23
    »¿
    2.11
    »
    2.08
    ŀ
    2.08
    ¹
    2.07
    ¿½
    2.04
    ¸
    2.03
    Ŀ
    2.00
    Ħ
    1.98
    Activations Density 0.269%

    No Known Activations