© 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. 9-RES-JB
    11. 24184
    Prev
    Next
    INDEX
    Explanations

    questions related to personal experiences and feelings

    oai_token-act-pair · gpt-3.5-turbo

    questions or prompts that inquire about experiences or opinions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    seless
    -0.70
     Worse
    -0.69
    .")
    -0.68
    hur
    -0.67
    $$$$
    -0.67
    adr
    -0.63
     Godd
    -0.62
     Stupid
    -0.61
    aunder
    -0.61
    arte
    -0.59
    POSITIVE LOGITS
     yourselves
    1.05
     yourself
    1.00
    )?
    0.79
     experien
    0.75
    ?:
    0.74
    ?ãĢį
    0.72
     your
    0.66
     autobi
    0.66
    ?
    0.64
    .?
    0.64
    Activations Density 0.339%

    No Known Activations