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. 7-RES-JB
    6. 15983
    Prev
    Next
    INDEX
    Explanations

    significant events or changes that have occurred since a specific point in time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a timeline or duration of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bart
    -0.82
    pta
    -0.80
    abus
    -0.78
    ×Ļ
    -0.73
    BILITIES
    -0.70
    isons
    -0.69
    tin
    -0.67
    acus
    -0.67
    ODY
    -0.67
    amus
    -0.66
    POSITIVE LOGITS
    rely
    1.14
     inception
    0.93
     2009
    0.81
    ĸļ
    0.81
     1945
    0.80
     infancy
    0.79
     2006
    0.79
     1950
    0.78
     1998
    0.78
     1999
    0.78
    Activations Density 0.048%

    No Known Activations