© 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. 8-RES-JB
    11. 3825
    Prev
    Next
    INDEX
    Explanations

    phrases indicating hesitation or reluctance

    oai_token-act-pair · gpt-3.5-turbo

    expressions of reluctance or resistance to discuss certain topics

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

    No Comments

    Negative Logits
    iple
    -0.69
     doubtless
    -0.64
    eele
    -0.62
     Millennium
    -0.60
     unparalleled
    -0.58
    ggles
    -0.57
     excellent
    -0.57
    not
    -0.57
     emerges
    -0.56
    zzi
    -0.56
    POSITIVE LOGITS
     anymore
    1.75
     anything
    1.21
     nor
    1.12
     any
    1.09
     anybody
    1.00
     ANY
    0.95
     anyone
    0.93
     unless
    0.91
     anywhere
    0.90
    anything
    0.88
    Activations Density 0.547%

    No Known Activations