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. 19012
    Prev
    Next
    INDEX
    Explanations

    names or terms related to technology products or features

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "rap" in various contexts

    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
    bright
    -0.65
    nen
    -0.64
     Takeru
    -0.63
     Giovanni
    -0.62
     disapp
    -0.61
    CHR
    -0.60
     Pwr
    -0.60
     wills
    -0.60
     Jolly
    -0.57
     err
    -0.56
    POSITIVE LOGITS
    hene
    1.05
    artisan
    0.99
    ascal
    0.92
    olitics
    0.91
    ixel
    0.91
    ackets
    0.91
    odcast
    0.90
    aging
    0.89
    rap
    0.89
    heny
    0.87
    Activations Density 0.027%

    No Known Activations