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. 8-RES-JB
    6. 4739
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of slowing down or decreasing speed

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to slowing down or decreasing speed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kefeller
    -0.70
    ä¿
    -0.69
    ب
    -0.65
    TY
    -0.65
    ãĥ¼ãĥĨãĤ£
    -0.64
    Ô
    -0.64
    ا
    -0.63
    cat
    -0.62
    å½
    -0.62
    row
    -0.61
    POSITIVE LOGITS
    grading
    0.91
     considerably
    0.91
    grades
    0.86
    graded
    0.83
    gradation
    0.76
    amina
    0.75
     nerv
    0.71
     slightly
    0.69
    baugh
    0.69
     accordingly
    0.68
    Activations Density 0.072%

    No Known Activations