© 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. 10-RES-JB
    11. 3229
    Prev
    Next
    INDEX
    Explanations

    hyperlinks and titles indicating a viewer's perspective to direct attention to specific content

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "View" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cffff
    -0.68
    ussian
    -0.66
    vernment
    -0.66
     indo
    -0.64
    ascal
    -0.64
    iques
    -0.61
    apo
    -0.60
     abstinence
    -0.60
     shroud
    -0.59
    bara
    -0.59
    POSITIVE LOGITS
    ership
    1.24
     largeDownload
    1.20
     Caption
    1.00
    ById
    0.96
    ers
    0.92
     Transcript
    0.90
     Images
    0.88
    points
    0.85
     photos
    0.84
    topic
    0.84
    Activations Density 0.020%

    No Known Activations