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. 1-RES-JB
    6. 17082
    Prev
    Next
    INDEX
    Explanations

    references to educational courses or programs

    oai_token-act-pair · gpt-3.5-turbo

    references to educational courses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stake
    -0.65
     inflated
    -0.64
     influential
    -0.60
     compar
    -0.60
    mented
    -0.59
     assisted
    -0.58
     unnamed
    -0.58
     sacrificed
    -0.58
     wrench
    -0.57
     spect
    -0.57
    POSITIVE LOGITS
    Course
    1.63
     Course
    1.43
    course
    1.35
     courses
    1.18
     course
    1.09
     COUR
    1.08
    ourses
    0.88
     instructors
    0.77
    gage
    0.76
    xual
    0.76
    Activations Density 0.021%

    No Known Activations