© 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. 10-RES-JB
    11. 24538
    Prev
    Next
    INDEX
    Explanations

    specific symbols or characters

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to uncertainty or futurity

    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
     favour
    -0.85
     incorpor
    -0.82
     favor
    -0.82
     inspir
    -0.80
     phenomen
    -0.78
     clitor
    -0.78
     pigeon
    -0.76
     tyres
    -0.75
     appropri
    -0.73
     tides
    -0.73
    POSITIVE LOGITS
    ï¸ı
    1.39
    ccording
    1.10
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.99
    RELATED
    0.98
    âĶĢâĶĢ
    0.96
    Published
    0.94
     Advertisement
    0.94
     VIDEOS
    0.94
    ãĥ´ãĤ¡
    0.91
    Roberts
    0.90
    Activations Density 0.116%

    No Known Activations