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. 11-RES-JB
    6. 18181
    Prev
    Next
    INDEX
    Explanations

    specific technical instructions or commands

    oai_token-act-pair · gpt-3.5-turbo

    elements of programming or coding structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ARDS
    -0.90
     nightmares
    -0.80
    ards
    -0.80
    reports
    -0.80
    girls
    -0.78
    wolves
    -0.78
    fires
    -0.76
    venants
    -0.76
     ceilings
    -0.76
    umes
    -0.76
    POSITIVE LOGITS
     element
    1.30
     item
    1.28
     parameter
    1.23
     row
    1.21
     byte
    1.20
     value
    1.17
     integer
    1.17
     node
    1.17
     occurrence
    1.15
     line
    1.11
    Activations Density 0.156%

    No Known Activations