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. 10-RES-JB
    6. 4003
    Prev
    Next
    INDEX
    Explanations

    directory names in file paths

    oai_token-act-pair · gpt-3.5-turbo

    references to directory structures and file organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    conduct
    -0.78
    acted
    -0.74
    acting
    -0.73
    uca
    -0.72
    pter
    -0.71
    Ò
    -0.71
    akening
    -0.70
    oria
    -0.68
    iating
    -0.67
    aughs
    -0.67
    POSITIVE LOGITS
     directory
    1.02
     ~/.
    1.00
     '/
    0.97
     folder
    0.97
     "/
    0.96
     (/
    0.93
    ystem
    0.92
     folders
    0.91
    =/
    0.91
     hierarchy
    0.90
    Activations Density 0.041%

    No Known Activations