© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 14133
    Prev
    Next
    INDEX
    Explanations

    Proper nouns, especially related to politics and economics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to academic or critical discussions, particularly those involving policies, choices, and systemic issues

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    к
    -0.68
    ãĥł
    -0.65
    ãĤ¸
    -0.64
    ãĤ«
    -0.62
    ãĤ©
    -0.61
    VERTISEMENT
    -0.61
    opol
    -0.61
    éĸ
    -0.61
    ril
    -0.61
    ãĥ¼ãĥ
    -0.60
    POSITIVE LOGITS
     and
    0.57
     uncond
    0.57
     urgently
    0.55
     realise
    0.54
     Gibbs
    0.53
     woke
    0.53
     apologise
    0.52
     whilst
    0.52
     *)
    0.52
     everywhere
    0.50
    Activations Density 1.298%

    No Known Activations