© 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. 7-RES-JB
    11. 17757
    Prev
    Next
    INDEX
    Explanations

    professionals or individuals by their titles or roles

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals introduced with "who."

    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
     Anything
    -0.67
     Dominion
    -0.67
     Federation
    -0.66
    ³³³³
    -0.66
     VIDEOS
    -0.61
     Guys
    -0.59
     Delicious
    -0.59
     Bound
    -0.59
     drying
    -0.57
    ãĤª
    -0.57
    POSITIVE LOGITS
     frequ
    1.05
     specializes
    1.03
     accompanies
    1.03
     oversaw
    1.01
     resided
    1.00
     preceded
    0.99
     attends
    0.98
     attended
    0.96
     lived
    0.92
     accompanied
    0.92
    Activations Density 0.141%

    No Known Activations