© 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. 2961
    Prev
    Next
    INDEX
    Explanations

    entities with a specific formatting structure

    oai_token-act-pair · gpt-3.5-turbo

    references to sports events or sports-related news

    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
     detract
    -0.68
     decrypt
    -0.68
     scrap
    -0.67
     fors
    -0.66
    aterasu
    -0.64
     obliter
    -0.63
     favour
    -0.63
     releg
    -0.62
     diseng
    -0.61
     discarded
    -0.61
    POSITIVE LOGITS
    ccording
    0.98
    HOU
    0.83
    Sources
    0.79
    Joined
    0.78
    Dallas
    0.76
    Details
    0.76
    LOS
    0.75
    Interested
    0.75
    Technology
    0.75
    Houston
    0.75
    Activations Density 0.573%

    No Known Activations