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. 3-RES-JB
    6. 10363
    Prev
    Next
    INDEX
    Explanations

    words related to physical or metaphorical boundaries

    oai_token-act-pair · gpt-3.5-turbo

    references to boundaries and limits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulz
    -0.89
    orah
    -0.85
    fortune
    -0.81
    obe
    -0.78
    kus
    -0.76
    enza
    -0.75
    weeney
    -0.73
    otos
    -0.71
    jury
    -0.71
    entanyl
    -0.70
    POSITIVE LOGITS
     boundaries
    1.35
     boundary
    1.17
     Bound
    0.90
     markers
    0.84
     deline
    0.81
     crossings
    0.79
     separating
    0.79
     delim
    0.77
     limits
    0.75
     dividing
    0.75
    Activations Density 0.013%

    No Known Activations