Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11014
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to political figures or positions

    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 @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sci
    -0.76
     scrape
    -0.75
    lees
    -0.64
    âľ
    -0.63
    als
    -0.61
     sprites
    -0.61
    atta
    -0.60
    ãĤ¦ãĤ¹
    -0.60
     destro
    -0.59
    -+
    -0.58
    POSITIVE LOGITS
     President
    3.50
    President
    2.92
     president
    2.60
     Presidents
    2.44
     PRESIDENT
    2.36
    president
    2.27
     presidents
    2.15
     Presidency
    1.92
     Presidential
    1.91
     Chairman
    1.91
    Activations Density 0.032%

    No Known Activations