Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 12494
    Prev
    Next
    INDEX
    Explanations

    surprising events or elements

    oai_token-act-pair · gpt-3.5-turbo

    words related to surprise or unexpected events

    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
    Ͻ
    -0.89
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.71
    Ç
    -0.69
    ``
    -0.68
    ————
    -0.68
    HCR
    -0.66
    ////////
    -0.64
     istg
    -0.63
    gpu
    -0.62
    âķIJâķIJ
    -0.62
    POSITIVE LOGITS
    ables
    0.71
    ibles
    0.70
    osher
    0.67
     limits
    0.67
    zbollah
    0.63
    awed
    0.63
     advis
    0.63
    istine
    0.62
    ickets
    0.61
    oct
    0.60
    Activations Density 0.000%

    No Known Activations