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. 4675
    Prev
    Next
    INDEX
    Explanations

    words related to sensitivity or controversy

    oai_token-act-pair · gpt-3.5-turbo

    words related to sensitivity and allergic reactions

    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
     millenn
    -0.79
    attribute
    -0.65
    iband
    -0.63
    asonry
    -0.63
    CAST
    -0.62
    DragonMagazine
    -0.62
    inately
    -0.59
    issions
    -0.59
    riel
    -0.59
     condem
    -0.59
    POSITIVE LOGITS
    onne
    0.70
    ioned
    0.69
     Born
    0.68
    otte
    0.66
    nil
    0.64
     Colour
    0.64
    ymes
    0.63
     breeds
    0.62
    orer
    0.62
    daq
    0.62
    Activations Density 0.000%

    No Known Activations