© 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. 20402
    Prev
    Next
    INDEX
    Explanations

    phrases related to allowing or permitting something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize obligations or permissions related to actions

    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
    enegger
    -0.75
    ELD
    -0.73
    ¯
    -0.73
    liest
    -0.72
    onday
    -0.72
    ipping
    -0.69
     Cosponsors
    -0.66
     Increasing
    -0.66
    ECTION
    -0.64
     [/
    -0.63
    POSITIVE LOGITS
     shine
    0.96
     dictate
    0.88
     breathe
    0.87
     flourish
    0.86
     slip
    0.85
     expire
    0.85
     lapse
    0.82
     slide
    0.81
    tera
    0.80
     handle
    0.80
    Activations Density 0.117%

    No Known Activations