© 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 EvalsExportsinterp-engineNEWAPI 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. 11403
    Prev
    Next
    INDEX
    Explanations

    terms or phrases related to comparison or evaluation based on specific criteria

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express comparisons or analyses related to specific concepts or topics

    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
     Cosponsors
    -0.89
    idel
    -0.89
    fort
    -0.80
    jad
    -0.80
    atan
    -0.78
    sup
    -0.75
    ©¶æ¥µ
    -0.75
    bay
    -0.75
    icer
    -0.74
    hid
    -0.74
    POSITIVE LOGITS
     sheer
    1.18
     aesthetics
    1.01
     usefulness
    0.95
     longevity
    0.95
     firepower
    0.95
     convenience
    0.95
     quality
    0.95
     demographics
    0.94
     visuals
    0.94
     sophistication
    0.93
    Activations Density 0.072%

    No Known Activations