© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 2587
    Prev
    Next
    INDEX
    Explanations

    specific mentions of different generations

    oai_token-act-pair · gpt-3.5-turbo

    references to different generations and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amina
    -0.85
    aleigh
    -0.85
    yer
    -0.76
    pmwiki
    -0.76
    eneg
    -0.71
    olulu
    -0.68
    abre
    -0.68
    acly
    -0.67
    imon
    -0.66
    ioxide
    -0.66
    POSITIVE LOGITS
     Generations
    0.99
     generations
    0.97
     inher
    0.93
     generation
    0.84
     generational
    0.79
     Generation
    0.73
    naire
    0.72
     ages
    0.72
     Lear
    0.71
     olds
    0.70
    Activations Density 0.032%

    No Known Activations