© 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. 24186
    Prev
    Next
    INDEX
    Explanations

    words related to beautiful or impressive things or experiences

    oai_token-act-pair · gpt-3.5-turbo

    expressions that emphasize something remarkable or impressive

    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
    ©¶æ
    -0.84
    ppo
    -0.79
    pora
    -0.73
    appa
    -0.72
    avez
    -0.68
    bid
    -0.66
     Prev
    -0.63
    haps
    -0.63
     foresee
    -0.62
    ordon
    -0.62
    POSITIVE LOGITS
     stunning
    1.12
    ly
    1.10
     breathtaking
    0.93
    ulously
    0.88
     gorgeous
    0.80
     visuals
    0.79
     naked
    0.78
    NESS
    0.76
    htaking
    0.76
    issance
    0.75
    Activations Density 0.007%

    No Known Activations