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. 3886
    Prev
    Next
    INDEX
    Explanations

    technical symbols and possibly different languages

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the end-of-text marker

    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
     destro
    -0.88
     disadvant
    -0.76
     undermin
    -0.74
     conclud
    -0.67
     agre
    -0.66
    aturdays
    -0.64
     referen
    -0.61
     hemor
    -0.60
     eleph
    -0.60
     explan
    -0.59
    POSITIVE LOGITS
     partName
    0.52
     âĢº
    0.51
     isEnabled
    0.48
    ==
    0.45
    info
    0.45
    \":
    0.44
    pt
    0.44
    1945
    0.43
    Ret
    0.43
    irt
    0.43
    Activations Density 0.369%

    No Known Activations