© 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 EvalsExportsAPI 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. 18240
    Prev
    Next
    INDEX
    Explanations

    phrases indicating assumptions or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing assumptions or beliefs about societal issues

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    guard
    -0.78
    ensed
    -0.71
    WER
    -0.71
    yna
    -0.70
    backer
    -0.70
    arthed
    -0.69
    inar
    -0.69
    eng
    -0.69
    hm
    -0.68
    AZ
    -0.66
    POSITIVE LOGITS
     somehow
    0.90
     someday
    0.82
     everyone
    0.81
     everything
    0.79
     they
    0.76
     rationality
    0.75
     anyone
    0.74
     these
    0.72
     abandoning
    0.71
     justifies
    0.69
    Activations Density 0.192%

    No Known Activations