© 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. 6-RES-JB
    11. 2718
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names ending with 'n'

    oai_token-act-pair · gpt-3.5-turbo

    references to specific people, particularly with the name "Brennan."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enne
    -0.84
    erb
    -0.76
     Rocks
    -0.73
    ade
    -0.72
    enko
    -0.70
     Hulk
    -0.69
    ©
    -0.69
    Lago
    -0.67
    OY
    -0.66
     Gaul
    -0.65
    POSITIVE LOGITS
    sworth
    0.88
    netflix
    0.85
    shot
    0.80
    isites
    0.78
     Fargo
    0.76
    ĵĺ
    0.75
    gency
    0.73
    ividual
    0.72
    ancial
    0.71
    hammad
    0.70
    Activations Density 0.071%

    No Known Activations