© 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. 7-RES-JB
    11. 20678
    Prev
    Next
    INDEX
    Explanations

    words related to physical structures or constructions

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to specific nouns and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įå¥ij士
    -0.81
     Kodi
    -0.73
    lessly
    -0.66
     Panther
    -0.65
     Detective
    -0.65
     Brewing
    -0.63
     sear
    -0.62
     Diagn
    -0.62
    less
    -0.62
    theless
    -0.62
    POSITIVE LOGITS
    ctions
    1.21
    ancies
    1.13
    gments
    1.12
    itions
    1.10
    ues
    1.10
    atures
    1.08
    estones
    1.07
    iences
    1.07
    ª
    1.05
    ptions
    1.04
    Activations Density 0.267%

    No Known Activations