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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2500
    Prev
    Next
    INDEX
    Explanations

    references to technical activities or instructions

    oai_token-act-pair · gpt-3.5-turbo
    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
    advertising
    -0.89
    èĢħ
    -0.80
    2019
    -0.75
    ã
    -0.73
     licens
    -0.72
    Cele
    -0.69
     prostitution
    -0.68
     solicitation
    -0.68
    ultural
    -0.68
     stigmat
    -0.68
    POSITIVE LOGITS
     myself
    1.05
     Asus
    0.97
     Setup
    0.93
     calibrated
    0.93
     setup
    0.92
    Setup
    0.91
     Corsair
    0.90
     my
    0.88
     WD
    0.86
     calibration
    0.85
    Activations Density 0.703%

    No Known Activations