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. 8-RES-JB
    6. 5763
    Prev
    Next
    INDEX
    Explanations

    names or words with a commonality in containing the pattern "ast", often related to academic institutions or people's names

    oai_token-act-pair · gpt-3.5-turbo

    affixes or suffixes commonly associated with certain word families, particularly in scientific or academic 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
    glers
    -0.77
     hail
    -0.71
     cones
    -0.65
     bother
    -0.61
     fork
    -0.59
     viability
    -0.59
     fumble
    -0.59
     entrepreneurship
    -0.57
     Cosmos
    -0.57
     cigars
    -0.57
    POSITIVE LOGITS
    wered
    1.07
    illary
    1.02
    heim
    0.93
    otropic
    0.92
    imity
    0.91
    obic
    0.83
    imov
    0.81
    orage
    0.81
    ibo
    0.80
    andre
    0.80
    Activations Density 0.050%

    No Known Activations