© 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. 0-RES-JB
    11. 11442
    Prev
    Next
    INDEX
    Explanations

    references to famous or noteworthy individuals

    oai_token-act-pair · gpt-3.5-turbo

    words related to legendary figures or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artment
    -0.75
    iard
    -0.72
    nesses
    -0.66
    election
    -0.66
    ICES
    -0.65
    Economic
    -0.64
    Newsletter
    -0.63
    ploy
    -0.63
     è£ıè¦ļéĨĴ
    -0.63
    20439
    -0.62
    POSITIVE LOGITS
     legend
    4.14
     legends
    3.31
     Legend
    2.27
    Legend
    2.21
     folklore
    1.78
     myth
    1.70
     legendary
    1.60
     lore
    1.46
     mythology
    1.43
     Legends
    1.41
    Activations Density 0.020%

    No Known Activations