© 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. 8-RES-JB
    11. 17254
    Prev
    Next
    INDEX
    Explanations

    accounts or descriptions of events or experiences

    oai_token-act-pair · gpt-3.5-turbo

    narrative storytelling elements that involve recounting events or descriptions of experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahead
    -0.70
    division
    -0.70
    inton
    -0.68
    MAS
    -0.67
    ature
    -0.66
    pole
    -0.65
    lead
    -0.63
    mas
    -0.63
    ãĥ¯
    -0.62
    gate
    -0.61
    POSITIVE LOGITS
     harrowing
    1.14
     experiences
    0.99
     firsthand
    0.97
     encounters
    0.97
     vividly
    0.94
     hardships
    0.94
     ordeal
    0.92
     frustrations
    0.90
     adventures
    0.90
     struggles
    0.89
    Activations Density 0.259%

    No Known Activations