© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 6420
    Prev
    Next
    INDEX
    Explanations

    mentions of leaks or sensitive information

    oai_token-act-pair · gpt-3.5-turbo

    references to leaks and narratives related to storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Baxter
    -0.76
     Pryor
    -0.68
     Kahn
    -0.68
    avan
    -0.67
     QC
    -0.66
     Fowler
    -0.65
     Moff
    -0.65
     solicitor
    -0.63
     editing
    -0.63
     Wong
    -0.61
    POSITIVE LOGITS
    Leaks
    2.57
    tale
    2.54
    igl
    1.73
     VIDEOS
    1.69
    kos
    1.31
    scenes
    1.15
    acular
    1.12
    ricular
    1.07
    minster
    1.06
    entimes
    1.00
    Activations Density 0.054%

    No Known Activations