© 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. 10-RES-JB
    11. 5419
    Prev
    Next
    INDEX
    Explanations

    quotations

    oai_token-act-pair · gpt-3.5-turbo

    quotations or dialogue tags in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     princip
    -0.78
     revol
    -0.71
     prone
    -0.67
     tabloid
    -0.66
     CPS
    -0.66
     hemor
    -0.65
     haunted
    -0.65
     pitted
    -0.64
     Borders
    -0.64
     sidx
    -0.64
    POSITIVE LOGITS
    Hey
    1.48
    Okay
    1.42
    Oh
    1.41
    hey
    1.40
    OK
    1.34
    Look
    1.34
    Yeah
    1.32
    Well
    1.31
    Wait
    1.26
    yeah
    1.25
    Activations Density 0.058%

    No Known Activations