© 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. 2-RES-JB
    11. 23082
    Prev
    Next
    INDEX
    Explanations

    fluctuations in the score on the jelly-related term

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "jelly."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rish
    -0.79
     reper
    -0.76
    VERTIS
    -0.71
    displayText
    -0.68
    VK
    -0.67
    drawn
    -0.67
    rival
    -0.67
    âĢ¢âĢ¢
    -0.64
    PLIED
    -0.64
    yrim
    -0.63
    POSITIVE LOGITS
    elly
    1.14
    bean
    0.89
     Bean
    0.86
    weed
    0.78
    archy
    0.76
    gorithm
    0.75
    fish
    0.75
    ounge
    0.71
     Beans
    0.71
    omon
    0.70
    Activations Density 0.012%

    No Known Activations