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

    Neuronpedia

    APICircuit 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. 6-RES-JB
    6. 11440
    Prev
    Next
    INDEX
    Explanations

    phrases related to evaluations or judgments such as 'very sad', 'positive comments', or 'economic situation'

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing financial issues or burdens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gio
    -0.81
    hement
    -0.78
    ican
    -0.73
    ichick
    -0.72
    negie
    -0.71
    icans
    -0.71
    rays
    -0.70
    ustom
    -0.69
    ror
    -0.69
    anos
    -0.69
    POSITIVE LOGITS
    é¾įå¥ij士
    0.92
    Scotland
    0.87
    Comment
    0.83
    FACE
    0.80
    ãĤ´ãĥ³
    0.79
    Wilson
    0.78
    Reviewed
    0.78
    ccording
    0.77
    JUST
    0.76
    UTC
    0.76
    Activations Density 0.088%

    No Known Activations