© 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. 20308
    Prev
    Next
    INDEX
    Explanations

    names containing 'Brien' or 'Reilly'

    oai_token-act-pair · gpt-3.5-turbo

    names of people, particularly those involved in media or commentary

    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
    ku
    -0.68
    fill
    -0.64
    hered
    -0.63
    rises
    -0.62
     mileage
    -0.60
    inations
    -0.60
    urious
    -0.59
    Solar
    -0.58
    ultan
    -0.56
     achievable
    -0.56
    POSITIVE LOGITS
    patrick
    0.80
    acht
    0.73
    ogl
    0.72
    tainment
    0.70
    ODUCT
    0.69
    hler
    0.69
    AMA
    0.69
    ishi
    0.68
    TD
    0.67
    stal
    0.67
    Activations Density 0.032%

    No Known Activations