© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 12382
    Prev
    Next
    INDEX
    Explanations

    photographs or mentions of photographs with potential purchase options

    oai_token-act-pair · gpt-3.5-turbo

    mentions of buying or purchasing photos

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.70
    azer
    -0.69
    hed
    -0.69
    icion
    -0.68
    worldly
    -0.68
    Austral
    -0.68
    oxide
    -0.67
    raid
    -0.65
    ilic
    -0.64
    netflix
    -0.64
    POSITIVE LOGITS
     Story
    0.88
     File
    0.74
    CLOSE
    0.72
     FILE
    0.71
    Buy
    0.71
     Practices
    0.70
     BY
    0.68
     Photo
    0.67
     Download
    0.65
     Wait
    0.65
    Activations Density 0.014%

    No Known Activations