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

    Neuronpedia

    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. 7391
    Prev
    Next
    INDEX
    Explanations

    measurement values and units of measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, particularly related to measurements and time indicators

    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
     Credit
    -0.72
     Freak
    -0.70
     Finger
    -0.67
    Rating
    -0.67
    achev
    -0.64
     Fault
    -0.62
     Cosponsors
    -0.62
     FACE
    -0.62
     lag
    -0.62
    Minor
    -0.60
    POSITIVE LOGITS
     650
    1.34
     550
    1.34
     850
    1.32
     600
    1.31
     800
    1.28
     400
    1.27
     475
    1.27
     700
    1.26
     500
    1.25
     750
    1.25
    Activations Density 0.227%

    No Known Activations