© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 13395
    Prev
    Next
    INDEX
    Explanations

    words related to different styles and aspects of dance

    oai_token-act-pair · gpt-3.5-turbo

    references to dance music and dance-related activities

    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
    omo
    -0.68
    PF
    -0.66
    aunder
    -0.65
    agar
    -0.65
    arah
    -0.64
    arez
    -0.63
    eger
    -0.62
     gracious
    -0.61
    aples
    -0.61
    ACTED
    -0.61
    POSITIVE LOGITS
     Dance
    0.94
    rers
    0.91
    floor
    0.91
     dance
    0.91
     ballet
    0.87
    hall
    0.86
     dances
    0.85
    goers
    0.85
    flo
    0.85
     Dancing
    0.84
    Activations Density 0.009%

    No Known Activations