© 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. 19656
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names likely related to a person named Layla and occurrences of the word 'layoffs' in a text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual named "Layla" and references to layoffs

    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
    ãĥ¯
    -0.74
    ãĥĦ
    -0.72
    iveness
    -0.70
    isks
    -0.67
     Gemini
    -0.67
    ilee
    -0.66
     Nero
    -0.66
    Balt
    -0.66
    >>\
    -0.66
    ãĥ¼ãĥĨãĤ£
    -0.65
    POSITIVE LOGITS
     Lay
    1.20
    Lay
    1.10
    ©¶æ
    0.89
    sheets
    0.87
    outs
    0.86
    holder
    0.81
    inois
    0.80
    ighton
    0.79
    ayers
    0.79
    lay
    0.78
    Activations Density 0.004%

    No Known Activations