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. 6-RES-JB
    6. 12928
    Prev
    Next
    INDEX
    Explanations

    adjectives describing high visual impact or beauty

    oai_token-act-pair · gpt-3.5-turbo

    descriptive words related to beauty and impressiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pora
    -0.78
    appa
    -0.73
    ploma
    -0.70
    ©¶æ
    -0.69
    ppo
    -0.69
    avez
    -0.68
    REL
    -0.66
     coli
    -0.65
    atives
    -0.64
    eper
    -0.62
    POSITIVE LOGITS
    ly
    1.62
    LY
    1.00
    ulously
    0.93
    ously
    0.86
    NESS
    0.82
    ingly
    0.78
    omical
    0.77
    htaking
    0.77
     spectacle
    0.75
     breathtaking
    0.75
    Activations Density 0.046%

    No Known Activations