© 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. 2-RES-JB
    11. 20699
    Prev
    Next
    INDEX
    Explanations

    mentions of "pro" related to professionalism, expertise, or specific roles

    oai_token-act-pair · gpt-3.5-turbo

    references to professional or pro-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.93
    ãĤ¼ãĤ¦ãĤ¹
    -0.76
     Dwell
    -0.76
     Flavoring
    -0.75
     Twain
    -0.70
     Halls
    -0.70
     Strait
    -0.68
    gow
    -0.67
     Preferred
    -0.66
    MORE
    -0.66
    POSITIVE LOGITS
    digy
    1.42
    verbs
    1.11
    actively
    0.94
     wrestler
    0.93
    oster
    0.92
    ccess
    0.91
    cedes
    0.87
    blems
    0.84
    pelling
    0.80
    secut
    0.80
    Activations Density 0.011%

    No Known Activations