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. 4-RES-JB
    6. 21739
    Prev
    Next
    INDEX
    Explanations

    references to societal issues and interactions involving decision making and opinions

    oai_token-act-pair · gpt-3.5-turbo

    references to the collective pronoun "they"

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

    No Comments

    Negative Logits
    CCC
    -0.86
     Eleven
    -0.79
     Kinn
    -0.74
     Amen
    -0.73
    CLASSIFIED
    -0.70
    ////////////////////////////////
    -0.69
     Club
    -0.68
     Kirin
    -0.66
    paragraph
    -0.64
    âĢ¢âĢ¢
    -0.63
    POSITIVE LOGITS
    're
    1.29
    've
    1.12
    'll
    1.07
    'd
    0.99
     selves
    0.97
    selves
    0.91
     conduc
    0.87
     could
    0.85
     reluct
    0.84
     perceive
    0.83
    Activations Density 0.283%

    No Known Activations