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. 8-RES-JB
    6. 282
    Prev
    Next
    INDEX
    Explanations

    important information related to summaries and schedules

    oai_token-act-pair · gpt-3.5-turbo

    various types of summaries and reviews associated with content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bably
    -0.94
     destro
    -0.74
    ovo
    -0.74
    sic
    -0.73
    romy
    -0.69
    cause
    -0.69
    ulz
    -0.69
     genetically
    -0.69
    resistant
    -0.69
     externalToEVAOnly
    -0.67
    POSITIVE LOGITS
     Sheet
    1.16
     Rankings
    1.13
     Show
    1.13
     Discussion
    1.11
     Detail
    1.11
     Transcript
    1.10
     Links
    1.07
     Contents
    1.07
     Manager
    1.05
     Description
    1.05
    Activations Density 0.210%

    No Known Activations