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. 4578
    Prev
    Next
    INDEX
    Explanations

    phrases related to socializing and gathering in various settings

    oai_token-act-pair · gpt-3.5-turbo
    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
     Detection
    -0.76
     retracted
    -0.76
     millenn
    -0.70
     proportional
    -0.69
    enders
    -0.69
     inacc
    -0.68
     withheld
    -0.68
     disabling
    -0.67
    ccording
    -0.66
    states
    -0.65
    POSITIVE LOGITS
     relax
    1.39
     enjoy
    1.31
     reminis
    1.31
     celebrate
    1.29
     bask
    1.23
     partake
    1.21
     indulge
    1.17
     hang
    1.16
     admire
    1.15
     interact
    1.15
    Activations Density 0.198%

    No Known Activations