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. 17273
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific group or team, potentially a crew or team name

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of "crew" or teams

    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
     ruby
    -0.74
     fluor
    -0.72
     pse
    -0.71
     fluoride
    -0.71
     deserts
    -0.69
     polarization
    -0.68
     immun
    -0.66
     ir
    -0.64
     indexed
    -0.64
     sed
    -0.63
    POSITIVE LOGITS
     Crew
    4.33
    Crew
    3.27
    crew
    2.24
     crew
    1.90
     crews
    1.70
     Jackets
    1.32
     Squad
    1.13
     Sounders
    1.09
     Columbus
    1.03
     Engineers
    1.00
    Activations Density 0.011%

    No Known Activations