© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20204
    Prev
    Next
    INDEX
    Explanations

    dimensions and measurements in millimeters and kilograms

    oai_token-act-pair · gpt-3.5-turbo

    quantitative measurements and numerical data

    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
    panic
    -0.83
    theme
    -0.82
    eco
    -0.78
    never
    -0.78
    why
    -0.78
    can
    -0.77
    historic
    -0.77
    selection
    -0.76
    anus
    -0.75
    DragonMagazine
    -0.75
    POSITIVE LOGITS
     mins
    1.08
     pounds
    1.06
     kW
    1.03
     cm
    1.03
     lbs
    1.02
     degrees
    1.01
     kg
    1.01
     hrs
    0.98
     inches
    0.97
     yards
    0.97
    Activations Density 0.132%

    No Known Activations