© 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. 11-RES-JB
    11. 10035
    Prev
    Next
    INDEX
    Explanations

    keywords related to various subjects like project management, coding, dating, and more

    oai_token-act-pair · gpt-3.5-turbo

    topics related to projects, business models, and various forms of products or markets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ACTIONS
    -0.86
    aves
    -0.85
    ints
    -0.85
    results
    -0.82
    azes
    -0.81
     extracts
    -0.80
    olds
    -0.78
     strokes
    -0.77
    attacks
    -0.77
    fixes
    -0.76
    POSITIVE LOGITS
     loophole
    1.14
     problem
    1.04
     shortage
    1.01
     clause
    1.00
     caveat
    0.95
     gap
    0.94
     somewhere
    0.94
     tendency
    0.94
     guy
    0.93
     resemblance
    0.93
    Activations Density 0.444%

    No Known Activations