© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 134
    Prev
    Next
    INDEX
    Explanations

    dates mentioned in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    year references in the text

    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
     periodic
    -0.67
     numbering
    -0.65
     domest
    -0.65
     rog
    -0.62
     unpredictable
    -0.61
     unexpl
    -0.61
     multic
    -0.61
     charm
    -0.61
     intrig
    -0.60
     cooperative
    -0.60
    POSITIVE LOGITS
    [/
    0.77
     Tweet
    0.77
    à¼
    0.73
    lez
    0.68
    quote
    0.68
    =#
    0.66
    advertising
    0.66
     }}
    0.66
    videos
    0.65
     Originally
    0.64
    Activations Density 0.021%

    No Known Activations