© 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. 4-RES-JB
    11. 24223
    Prev
    Next
    INDEX
    Explanations

    multi-word phrases mentioning discounts, promotions, or deals

    oai_token-act-pair · gpt-3.5-turbo

    promotional language related to games and bundles

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

    No Comments

    Negative Logits
     respectively
    -0.84
    judicial
    -0.70
     divest
    -0.69
    etheless
    -0.67
     fundament
    -0.66
    yright
    -0.64
    ancial
    -0.64
    ilater
    -0.63
    terday
    -0.63
    iversal
    -0.63
    POSITIVE LOGITS
     Profile
    0.86
     Mechdragon
    0.74
    Shield
    0.71
    Mini
    0.70
     Edit
    0.69
     Drops
    0.69
     Phant
    0.67
     âĢº
    0.64
     Mini
    0.64
    âĦ¢:
    0.64
    Activations Density 0.392%

    No Known Activations