© 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. 1731
    Prev
    Next
    INDEX
    Explanations

    words related to visibility or being visible

    oai_token-act-pair · gpt-3.5-turbo

    the word "visible" and its varying context in the document

    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
    upuncture
    -0.86
    allo
    -0.82
    rica
    -0.79
    nan
    -0.79
    inion
    -0.78
    req
    -0.77
    ese
    -0.75
    herent
    -0.74
    orously
    -0.74
    annis
    -0.73
    POSITIVE LOGITS
     signs
    0.89
     visible
    0.84
     Signs
    0.77
     veins
    0.74
     silhou
    0.70
     srfAttach
    0.70
    isable
    0.68
     signage
    0.68
     markers
    0.67
     billboards
    0.67
    Activations Density 0.031%

    No Known Activations