© 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. 3-RES-JB
    11. 6916
    Prev
    Next
    INDEX
    Explanations

    mentions of professionalism or professional standards

    oai_token-act-pair · gpt-3.5-turbo

    references to professionalism or professional standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    doors
    -0.76
    ĸļ
    -0.73
     Wick
    -0.72
    pty
    -0.68
    bows
    -0.65
     Ezekiel
    -0.64
    tags
    -0.64
    Trigger
    -0.64
    !/
    -0.64
     Twain
    -0.64
    POSITIVE LOGITS
     footballer
    0.98
     wrestler
    0.96
    digy
    0.92
     athlete
    0.90
     wrestling
    0.84
     athletes
    0.84
    ized
    0.81
     professional
    0.81
     gol
    0.80
     professionals
    0.77
    Activations Density 0.013%

    No Known Activations