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. 8639
    Prev
    Next
    INDEX
    Explanations

    data transfer rates, storage capacities, and other technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications and performance metrics

    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
     scapego
    -0.76
     lookout
    -0.75
    USS
    -0.72
    Je
    -0.68
     pund
    -0.67
     Borough
    -0.66
    Mail
    -0.63
     Tayyip
    -0.63
     fac
    -0.63
     grievance
    -0.62
    POSITIVE LOGITS
     Unloaded
    0.94
     increments
    0.86
     Width
    0.83
     diameter
    0.77
    iameter
    0.76
     GDDR
    0.76
    poons
    0.73
     Chill
    0.70
    âĪĴ
    0.70
    total
    0.70
    Activations Density 0.226%

    No Known Activations