© 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. 1-RES-JB
    11. 3216
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly focusing on the name "Lindsey"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those named Lindsey or Lindsay

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    haps
    -0.79
    arist
    -0.78
    avez
    -0.75
    ropri
    -0.71
    HAHAHAHA
    -0.70
    earing
    -0.70
    attled
    -0.70
    oteric
    -0.70
    requisite
    -0.69
    ilded
    -0.67
    POSITIVE LOGITS
     Lindsey
    1.28
     Buckingham
    1.01
     Graham
    0.98
     Hendricks
    0.82
     Stephens
    0.81
     Lindsay
    0.81
    say
    0.80
    sey
    0.80
     Von
    0.75
     Simpson
    0.74
    Activations Density 0.004%

    No Known Activations