© 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. 4-RES-JB
    11. 14744
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or political entities and actions

    oai_token-act-pair · gpt-3.5-turbo

    elements related to legal and governmental proceedings

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

    No Comments

    Negative Logits
    Weiss
    -0.84
     Hemisphere
    -0.80
     Beacon
    -0.80
     Pennsylvania
    -0.79
     Weiss
    -0.78
     Olson
    -0.77
     Grimm
    -0.77
     Tulsa
    -0.75
     Pittsburgh
    -0.74
     Asheville
    -0.73
    POSITIVE LOGITS
    jriwal
    1.18
    umbai
    1.14
     Hindi
    1.12
     lakh
    1.07
     Sharma
    1.06
     Tamil
    1.05
     Hindu
    1.04
     Modi
    1.02
    India
    1.01
     Aadhaar
    1.01
    Activations Density 1.296%

    No Known Activations