© 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. 10-RES-JB
    11. 18722
    Prev
    Next
    INDEX
    Explanations

    public statements or messages that are formally released

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in" and related contexts

    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
    issance
    -0.79
    VERTISEMENT
    -0.74
    Ħ¢
    -0.73
     someday
    -0.73
    Ĥª
    -0.69
    iful
    -0.68
    ģĸ
    -0.67
    (*
    -0.66
    âĿ
    -0.65
    âĶĢâĶĢâĶĢâĶĢ
    -0.64
    POSITIVE LOGITS
     favor
    1.07
     response
    1.03
     regards
    1.03
     favour
    1.02
     lieu
    0.98
     support
    0.96
     haste
    0.96
     relation
    0.95
     advance
    0.94
     anticipation
    0.92
    Activations Density 0.174%

    No Known Activations