© 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. 1-RES-JB
    11. 16425
    Prev
    Next
    INDEX
    Explanations

    phrases related to legendary figures or stories

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "legend" or "legends."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artment
    -0.81
     Parenthood
    -0.77
    emouth
    -0.70
    ells
    -0.70
    ouls
    -0.70
    avez
    -0.70
    atana
    -0.69
    sterdam
    -0.69
    NetMessage
    -0.68
    athetic
    -0.68
    POSITIVE LOGITS
     legend
    1.37
     legends
    1.23
    Legend
    1.01
     Legend
    0.94
    lore
    0.82
     tales
    0.81
    arily
    0.77
     rumours
    0.77
     Tales
    0.76
     Gord
    0.73
    Activations Density 0.007%

    No Known Activations