© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12692
    Prev
    Next
    INDEX
    Explanations

    words related to being impressed

    oai_token-act-pair · gpt-3.5-turbo

    expressions of admiration or being impressed

    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
    ©¶æ
    -0.71
    rules
    -0.70
    violence
    -0.70
    rama
    -0.69
    turn
    -0.66
    access
    -0.64
    andro
    -0.63
    nuclear
    -0.63
     diverted
    -0.63
    portion
    -0.63
    POSITIVE LOGITS
     impressed
    0.92
    mented
    0.77
    oresc
    0.76
     resemb
    0.74
     surprised
    0.74
    sson
    0.73
    MENTS
    0.72
    ulously
    0.71
    iated
    0.69
    ochet
    0.67
    Activations Density 0.012%

    No Known Activations