© 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. 3-RES-JB
    11. 8827
    Prev
    Next
    INDEX
    Explanations

    locations named "Burns"

    oai_token-act-pair · gpt-3.5-turbo

    references to the location "Burns."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilial
    -0.79
    eanor
    -0.77
    INAL
    -0.69
    ascal
    -0.68
    ntil
    -0.68
    awaru
    -0.66
    ortun
    -0.66
    pai
    -0.66
    role
    -0.66
    remlin
    -0.66
    POSITIVE LOGITS
     Burns
    1.19
    lee
    0.89
     Burn
    0.86
    leys
    0.83
    ville
    0.81
    LEY
    0.81
    ford
    0.81
    Burn
    0.79
    ley
    0.78
    lett
    0.78
    Activations Density 0.007%

    No Known Activations