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. 18143
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "This" followed by something specific

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "This" or statements that begin with "This."

    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
    unk
    -0.77
    aws
    -0.72
    ARS
    -0.69
    ickets
    -0.67
    amia
    -0.66
    rums
    -0.65
    ãĥīãĥ©
    -0.63
    oller
    -0.63
    icons
    -0.63
    istries
    -0.63
    POSITIVE LOGITS
     latter
    0.93
     contrasts
    0.93
     trope
    0.86
     phenomenon
    0.85
     discrepancy
    0.85
     culminated
    0.84
     particular
    0.84
     article
    0.84
     arrangement
    0.83
     subset
    0.78
    Activations Density 0.158%

    No Known Activations