© 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. 8-RES-JB
    11. 10350
    Prev
    Next
    INDEX
    Explanations

    mentions of events and developments in business and politics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of significant events and headlines in global or national contexts

    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
     ILCS
    -0.70
    anges
    -0.68
    enser
    -0.68
    Reason
    -0.66
    SPONSORED
    -0.64
    nery
    -0.61
     associ
    -0.61
    omorph
    -0.60
    Slot
    -0.60
     assum
    -0.59
    POSITIVE LOGITS
     yesterday
    1.64
     Tuesday
    1.46
     Wednesday
    1.46
     Thursday
    1.46
     Monday
    1.39
     Friday
    1.35
     Saturday
    1.16
     recently
    1.16
     Sunday
    1.15
    Thursday
    1.11
    Activations Density 1.044%

    No Known Activations