© 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. 8-RES-JB
    11. 15200
    Prev
    Next
    INDEX
    Explanations

    major or significant items or events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to size and scale

    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
    iquette
    -0.87
     Advice
    -0.73
     Bye
    -0.73
     café
    -0.67
     shy
    -0.66
     inconsist
    -0.66
     counselling
    -0.66
    tone
    -0.65
    iste
    -0.65
    ezvous
    -0.64
    POSITIVE LOGITS
     trillions
    1.02
     encomp
    1.01
     enorm
    1.01
     surpass
    1.00
     billions
    0.95
     unimaginable
    0.92
     colossal
    0.91
     exponentially
    0.91
     exceed
    0.91
     exceeds
    0.91
    Activations Density 0.920%

    No Known Activations