© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 22482
    Prev
    Next
    INDEX
    Explanations

    words related to computer programming or technical operations (such as 'script', 'run', 'file', 'code')

    oai_token-act-pair · gpt-3.5-turbo

    references to data processing or computational terms

    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
     Elliott
    -1.00
     Element
    -0.95
     Phi
    -0.94
    Ay
    -0.94
     Chandler
    -0.93
     PHI
    -0.85
    Ye
    -0.85
     Elements
    -0.85
    YE
    -0.85
     Ye
    -0.85
    POSITIVE LOGITS
    run
    1.13
     RUN
    1.02
    runs
    1.01
     Brun
    0.93
    ran
    0.92
     Run
    0.86
    oun
    0.86
    running
    0.86
     Rus
    0.84
    Run
    0.82
    Activations Density 0.407%

    No Known Activations