© 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. 20019
    Prev
    Next
    INDEX
    Explanations

    words related to diffusion or words ending in -usion

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "fusion."

    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
    mega
    -0.72
    tha
    -0.68
     unfinished
    -0.67
    runs
    -0.61
    Ķ
    -0.61
    estic
    -0.60
     Logged
    -0.57
    dule
    -0.57
     sailed
    -0.56
    animate
    -0.56
    POSITIVE LOGITS
    usion
    1.06
    usions
    0.92
    hower
    0.85
    oldemort
    0.81
    hole
    0.81
    ibility
    0.79
    ibles
    0.77
    usional
    0.76
     Emin
    0.74
    naire
    0.73
    Activations Density 0.016%

    No Known Activations