© 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. 9-RES-JB
    11. 21174
    Prev
    Next
    INDEX
    Explanations

    names of media or news outlets

    oai_token-act-pair · gpt-3.5-turbo

    references to specific publications and reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.84
    locks
    -0.77
    zees
    -0.71
    bands
    -0.69
    ËĪ
    -0.68
     isEnabled
    -0.66
    orsche
    -0.65
     Tradable
    -0.65
     ç¥ŀ
    -0.64
    oos
    -0.64
    POSITIVE LOGITS
     reporter
    0.98
     readers
    0.94
     reporters
    0.93
     Reporter
    0.86
    Dispatch
    0.86
     report
    0.85
     reviewer
    0.84
     columnist
    0.84
     reader
    0.83
     analysis
    0.83
    Activations Density 0.359%

    No Known Activations