© 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. 589
    Prev
    Next
    INDEX
    Explanations

    the name "AMY GOODMAN" and associated text

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific person, Amy Goodman, and her reporting or discussions

    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
    ateurs
    -0.67
    aden
    -0.65
    ĺħ
    -0.62
    phis
    -0.59
    Offline
    -0.59
    awed
    -0.59
    warts
    -0.59
    ħĭ
    -0.59
    istically
    -0.58
    matically
    -0.58
    POSITIVE LOGITS
     GOODMAN
    1.16
     PRESIDENT
    0.86
    :
    0.78
     EDITION
    0.75
    âĦ¢:
    0.70
     DU
    0.69
     NEXT
    0.68
     COVER
    0.68
     CALL
    0.68
    !:
    0.67
    Activations Density 0.020%

    No Known Activations