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. 6813
    Prev
    Next
    INDEX
    Explanations

    references to specific publications and dates

    oai_token-act-pair · gpt-3.5-turbo

    references to published works and their bibliographic details

    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
    goal
    -0.77
    arge
    -0.77
    oooooooo
    -0.75
    omorphic
    -0.74
    root
    -0.72
    orbit
    -0.68
    ndra
    -0.67
    erm
    -0.67
    angu
    -0.67
    animate
    -0.66
    POSITIVE LOGITS
     ISBN
    1.23
     pg
    1.10
     Retrieved
    1.10
     pp
    1.08
     reprinted
    1.07
     reprint
    1.01
     Accessed
    0.95
    published
    0.93
     unpublished
    0.93
     paperback
    0.92
    Activations Density 0.273%

    No Known Activations