© 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. 7-RES-JB
    11. 9601
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic disciplines or research fields

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¯¯¯¯
    -0.73
    âĸ¬âĸ¬
    -0.70
    ¯¯¯¯¯¯¯¯
    -0.69
     mileage
    -0.64
    SPONSORED
    -0.64
     blinded
    -0.57
    ////////////////////////////////
    -0.56
     corrid
    -0.56
    âĢ¦âĢ¦âĢ¦âĢ¦
    -0.56
     overwhel
    -0.56
    POSITIVE LOGITS
    dates
    1.50
    olicy
    1.25
    stairs
    1.17
    dating
    1.13
    edia
    1.09
    grades
    1.03
    odcast
    1.03
    inion
    1.01
    icult
    1.01
    rint
    1.00
    Activations Density 0.036%

    No Known Activations