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. 7209
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal interactions and conflicts

    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
    ossus
    -0.77
     cures
    -0.75
     prest
    -0.73
     staggered
    -0.72
     Keynes
    -0.72
     doomed
    -0.71
     unbeat
    -0.71
     unbeaten
    -0.71
     reinvent
    -0.70
     marvel
    -0.70
    POSITIVE LOGITS
     âĢ
    1.22
    âĢ
    1.17
     hijab
    1.07
     pronouns
    1.01
    ã
    0.94
     [+
    0.93
     GamerGate
    0.93
     harassment
    0.91
     disrespectful
    0.90
     offended
    0.86
    Activations Density 0.868%

    No Known Activations