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. 14589
    Prev
    Next
    INDEX
    Explanations

    percentages expressed in a decimal format

    oai_token-act-pair · gpt-3.5-turbo

    statistics related to unemployment rates

    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
     parach
    -0.69
    itionally
    -0.66
     plent
    -0.63
     assortment
    -0.62
     firsthand
    -0.62
     painstaking
    -0.61
     roam
    -0.61
     aisle
    -0.60
     pudding
    -0.60
     glow
    -0.59
    POSITIVE LOGITS
    47
    1.08
    56
    1.06
    09
    1.06
    07
    1.06
    08
    1.05
    04
    1.04
    38
    1.04
    49
    1.04
    58
    1.03
    9
    1.03
    Activations Density 0.117%

    No Known Activations