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. 2904
    Prev
    Next
    INDEX
    Explanations

    instructions related to assembling or setting up a technical device or system

    oai_token-act-pair · gpt-3.5-turbo

    instructions for assembly or installation processes

    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
    Topics
    -0.76
     Voting
    -0.67
     CrossRef
    -0.66
     Ranking
    -0.66
    icipated
    -0.66
    facts
    -0.65
     genomes
    -0.64
     Participation
    -0.64
    Publisher
    -0.63
    Narr
    -0.63
    POSITIVE LOGITS
     solder
    1.31
     attach
    1.24
     tighten
    1.15
     unsc
    1.12
     submer
    1.08
     mount
    1.08
     remove
    1.08
     weld
    1.07
     rotate
    1.07
     adjust
    1.06
    Activations Density 0.293%

    No Known Activations