© 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. 19291
    Prev
    Next
    INDEX
    Explanations

    email newsletter subscription prompts

    oai_token-act-pair · gpt-3.5-turbo

    headers or introductory phrases in content

    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
    MRI
    -0.68
     bases
    -0.65
    ../
    -0.62
    apy
    -0.61
    Magikarp
    -0.60
    pled
    -0.60
    ysis
    -0.60
    âĶ
    -0.59
     withd
    -0.59
    hesis
    -0.58
    POSITIVE LOGITS
     Slate
    0.81
    cloneembedreportprint
    0.76
     Updates
    0.75
     Daily
    0.74
     Middles
    0.73
     Fixes
    0.73
     notified
    0.72
     cele
    0.71
     Email
    0.70
    daily
    0.67
    Activations Density 0.044%

    No Known Activations