© 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. 2417
    Prev
    Next
    INDEX
    Explanations

    instances where something is discovered or determined

    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
    idium
    -0.69
    WARNING
    -0.65
    rolet
    -0.64
    isoft
    -0.63
    mort
    -0.63
    clock
    -0.62
    ignore
    -0.62
    mentioned
    -0.62
    IPS
    -0.62
     Mandatory
    -0.60
    POSITIVE LOGITS
     refuge
    1.07
     ways
    1.06
    ered
    1.01
     loopholes
    0.94
     shelter
    0.93
     traction
    0.83
     sanctuary
    0.82
     footing
    0.82
     fertile
    0.80
     footh
    0.79
    Activations Density 0.092%

    No Known Activations