© 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. 10-RES-JB
    11. 20430
    Prev
    Next
    INDEX
    Explanations

    keywords related to fictional characters, especially from popular culture

    oai_token-act-pair · gpt-3.5-turbo

    references to iconic characters and franchises in popular culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arij
    -0.94
    IENT
    -0.80
    ordable
    -0.79
    mination
    -0.77
    etheless
    -0.76
    REAM
    -0.75
    itutional
    -0.74
    significant
    -0.73
    ĵ
    -0.72
    GBT
    -0.71
    POSITIVE LOGITS
     Returns
    1.17
     Strikes
    1.09
     Unch
    1.06
     Adventures
    1.05
     Kenobi
    1.03
     Statue
    1.01
     Costume
    1.01
     Chronicles
    0.99
     costume
    0.98
     Jr
    0.96
    Activations Density 0.199%

    No Known Activations