© 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. 7-RES-JB
    11. 5105
    Prev
    Next
    INDEX
    Explanations

    names, likely related to a specific individual

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals and their attributes or achievements

    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
    zai
    -0.71
    bris
    -0.68
    apons
    -0.67
    arious
    -0.64
    zynski
    -0.63
    izophren
    -0.60
    bart
    -0.60
    artifacts
    -0.59
    zag
    -0.59
    asca
    -0.59
    POSITIVE LOGITS
     BaseType
    0.65
     =
    0.63
     consisted
    0.62
     predomin
    0.61
     rim
    0.61
    verages
    0.60
     alone
    0.60
     âĨĴ
    0.59
    âĨĴ
    0.58
     narrowly
    0.58
    Activations Density 0.596%

    No Known Activations