© 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. 15954
    Prev
    Next
    INDEX
    Explanations

    references to open-source software or projects

    oai_token-act-pair · gpt-3.5-turbo

    references to open source software and projects

    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
    awed
    -0.88
    ellen
    -0.83
    =-=-=-=-
    -0.81
    oola
    -0.80
    charg
    -0.75
    hof
    -0.74
    outer
    -0.73
    igne
    -0.73
     Kear
    -0.70
    ques
    -0.70
    POSITIVE LOGITS
     software
    1.05
     projects
    1.05
     repositories
    1.02
     repository
    0.94
     project
    0.93
     platforms
    0.91
     hardware
    0.89
     Projects
    0.86
     platform
    0.85
     frameworks
    0.85
    Activations Density 0.062%

    No Known Activations