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. 1346
    Prev
    Next
    INDEX
    Explanations

    terms related to educational or instructional activities

    oai_token-act-pair · gpt-3.5-turbo

    references to training programs and activities

    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
    osi
    -0.78
    vous
    -0.66
    portation
    -0.65
    ventory
    -0.63
    ogene
    -0.62
    itous
    -0.61
    peria
    -0.61
    eph
    -0.60
    510
    -0.60
    fff
    -0.59
    POSITIVE LOGITS
     Peaks
    0.92
    UFC
    0.84
     instructors
    0.84
     seminars
    0.83
     acad
    0.81
     manuals
    0.80
     exercises
    0.79
     academy
    0.76
     sessions
    0.75
    Training
    0.73
    Activations Density 0.042%

    No Known Activations