Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 20861
    Prev
    Next
    INDEX
    Explanations

    phrases related to identifying, acknowledging, and potentially solving various issues or problems

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to problems and their potential solutions

    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
     ceremonies
    -0.76
     dances
    -0.75
     slots
    -0.70
     nods
    -0.70
     ceremony
    -0.69
     Values
    -0.67
     choir
    -0.67
     chapel
    -0.66
     procession
    -0.65
    ramid
    -0.64
    POSITIVE LOGITS
     exacerbated
    1.17
     plag
    1.15
     worsened
    1.12
     severity
    1.09
     endemic
    1.08
     remed
    1.06
     caused
    1.06
     plague
    1.01
     unsolved
    1.00
     worsen
    0.98
    Activations Density 0.756%

    No Known Activations