© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 2448
    Prev
    Next
    INDEX
    Explanations

    dates mentioned in various formats

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to dates and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.63
    stories
    -0.61
    bably
    -0.59
    ancial
    -0.58
    itness
    -0.57
     reconc
    -0.54
     transitions
    -0.53
     pairs
    -0.52
    arkable
    -0.51
    ewitness
    -0.51
    POSITIVE LOGITS
    âĶĢâĶĢâĶĢâĶĢ
    0.85
    lol
    0.71
    \":
    0.70
     SetFontSize
    0.69
    scl
    0.68
     etc
    0.68
    isen
    0.66
     TBA
    0.66
    ¼
    0.66
    Jr
    0.66
    Activations Density 0.196%

    No Known Activations