© 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. 16062
    Prev
    Next
    INDEX
    Explanations

    information about personal anecdotes or accounts involving interaction and experience

    oai_token-act-pair · gpt-3.5-turbo

    mentions of storytelling or accounts of personal experiences

    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
    gate
    -0.71
    available
    -0.69
    clock
    -0.69
    icons
    -0.69
    Copy
    -0.68
    hold
    -0.68
    worthiness
    -0.68
    wei
    -0.67
    printf
    -0.66
    hm
    -0.66
    POSITIVE LOGITS
     experiences
    1.09
     harrowing
    1.06
     adventures
    1.00
     overcoming
    0.99
     hardships
    0.98
     encountering
    0.98
     struggles
    0.95
     frustrations
    0.95
     encounters
    0.93
     experience
    0.91
    Activations Density 0.304%

    No Known Activations