© 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. 9-RES-JB
    11. 20737
    Prev
    Next
    INDEX
    Explanations

    terms related to locations, numbers, and official titles

    oai_token-act-pair · gpt-3.5-turbo

    references to official citations and regulatory actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ÂŃ
    -1.10
     analys
    -1.06
     maths
    -1.03
     (£
    -1.02
     scept
    -1.01
     realised
    -1.00
     criticised
    -0.98
     Fifa
    -0.97
     analyse
    -0.96
    alys
    -0.95
    POSITIVE LOGITS
     thru
    1.26
     COUNTY
    1.13
     Veter
    0.95
     negro
    0.95
     Negro
    0.92
     Plaintiff
    0.91
     Owner
    0.91
     statewide
    0.90
     Spokane
    0.90
     Harbor
    0.90
    Activations Density 2.555%

    No Known Activations