© 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. 376
    Prev
    Next
    INDEX
    Explanations

    dates expressed in numbers

    oai_token-act-pair · gpt-3.5-turbo

    temporal phrases and references to specific periods or events

    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
    hazard
    -0.73
     Pastebin
    -0.71
    tap
    -0.66
    arest
    -0.66
     âĸĪ
    -0.65
    Leaks
    -0.65
    pdf
    -0.61
    PDF
    -0.60
    react
    -0.60
    emphasis
    -0.60
    POSITIVE LOGITS
    Born
    1.18
     Born
    1.12
     autobi
    0.97
     biography
    0.95
     founding
    0.89
     fame
    0.87
     stint
    0.86
    His
    0.79
    ventures
    0.78
    sequently
    0.78
    Activations Density 0.587%

    No Known Activations