© 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. 14738
    Prev
    Next
    INDEX
    Explanations

    phrases indicating belief or speculation

    oai_token-act-pair · gpt-3.5-turbo

    assertions of belief or speculation about people or situations

    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
    mentioned
    -0.75
    ample
    -0.70
    cloth
    -0.68
    Interstitial
    -0.68
    ãģį
    -0.68
    ECK
    -0.67
    Newsletter
    -0.67
    talk
    -0.64
    Against
    -0.62
    jab
    -0.60
    POSITIVE LOGITS
    lessly
    0.87
    fully
    0.78
     destined
    0.74
     responsible
    0.72
     haunted
    0.70
    ril
    0.70
     guilty
    0.67
     abducted
    0.65
     intact
    0.65
     unrelated
    0.65
    Activations Density 0.077%

    No Known Activations