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. 10-RES-JB
    6. 7663
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences starting with "First of all."

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "first of all."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ynes
    -0.66
    workers
    -0.59
    chrom
    -0.56
    obal
    -0.56
    weeney
    -0.56
    rav
    -0.55
    >]
    -0.54
    BO
    -0.54
    ansas
    -0.54
    taking
    -0.54
    POSITIVE LOGITS
     kin
    1.04
     equals
    0.94
     foremost
    0.86
     course
    0.82
    icial
    0.80
    ensibly
    0.76
    course
    0.73
    ortunately
    0.71
     nutshell
    0.69
     ali
    0.67
    Activations Density 0.029%

    No Known Activations