© 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. 24092
    Prev
    Next
    INDEX
    Explanations

    words related to high praise or admiration

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "brilliant" used as a descriptor

    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
    VR
    -0.86
    aver
    -0.78
    VI
    -0.76
    aper
    -0.74
    asta
    -0.74
    ople
    -0.71
    BD
    -0.70
    vere
    -0.70
    PU
    -0.70
    ratom
    -0.69
    POSITIVE LOGITS
     brilliance
    1.10
     brilliant
    1.07
     Brilliant
    0.90
     genius
    0.82
     brill
    0.80
     barr
    0.79
    ulously
    0.79
    NESS
    0.76
     stellar
    0.74
     talents
    0.73
    Activations Density 0.008%

    No Known Activations