© 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. 8-RES-JB
    11. 18710
    Prev
    Next
    INDEX
    Explanations

    titles or names of political or royal figures, especially relating to Indian Maharajas

    oai_token-act-pair · gpt-3.5-turbo

    titles and ranks of figures related to authority or leadership

    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
    zb
    -0.68
    illance
    -0.68
     crate
    -0.68
    atown
    -0.67
    camera
    -0.64
    ACA
    -0.62
     trail
    -0.62
    crew
    -0.61
    pless
    -0.59
    aver
    -0.59
    POSITIVE LOGITS
    esses
    1.14
    doms
    1.06
     Franz
    0.98
     Richard
    0.97
     Theodore
    0.97
     Gerald
    0.97
     John
    0.97
     Joseph
    0.97
     Ferdinand
    0.96
     William
    0.95
    Activations Density 0.283%

    No Known Activations