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. 0-RES-JB
    6. 21242
    Prev
    Next
    INDEX
    Explanations

    references to outer space or physical outermost layers

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "outer."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abet
    -0.88
    ãĤ¤ãĥĪ
    -0.68
    lik
    -0.67
    thanks
    -0.63
     Prompt
    -0.62
     Charity
    -0.62
     Petition
    -0.62
    HAHAHAHA
    -0.61
    haul
    -0.61
    pot
    -0.61
    POSITIVE LOGITS
     outer
    3.61
     Outer
    2.59
     inner
    2.05
    outer
    1.93
     Inner
    1.54
     outward
    1.43
     exterior
    1.41
     periphery
    1.24
     upper
    1.23
     inward
    1.19
    Activations Density 0.007%

    No Known Activations