© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 7111
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific entities related to diverse topics

    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
    ãĥ¯ãĥ³
    -0.76
    Firstly
    -0.72
    bg
    -0.69
    Appearance
    -0.68
    ãĥİ
    -0.67
    abilia
    -0.67
    FORMATION
    -0.66
    Cause
    -0.65
    Register
    -0.65
    acters
    -0.65
    POSITIVE LOGITS
     Chilean
    0.96
     Jordanian
    0.96
     Kazakh
    0.95
     Lithuan
    0.94
     Indones
    0.92
     Bahrain
    0.92
     Urug
    0.90
     Malaysian
    0.90
     Indonesian
    0.89
     Hungarian
    0.89
    Activations Density 0.744%

    No Known Activations