© 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. 1-RES-JB
    11. 20141
    Prev
    Next
    INDEX
    Explanations

    references to political figures, particularly presidents

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "President."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sensit
    -0.74
     fitt
    -0.74
     magnitude
    -0.71
    bane
    -0.70
     IMAGES
    -0.69
    âĶĢâĶĢâĶĢâĶĢ
    -0.69
     conditioning
    -0.67
     legs
    -0.65
     intoler
    -0.65
     vain
    -0.64
    POSITIVE LOGITS
    ial
    1.19
    ially
    1.15
    President
    0.98
    hip
    0.94
    IAL
    0.88
    clinton
    0.88
    doms
    0.85
    Donald
    0.84
    president
    0.82
     Barack
    0.81
    Activations Density 0.013%

    No Known Activations