© 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. 11-RES-JB
    11. 24573
    Prev
    Next
    INDEX
    Explanations

    names of companies or organizational entities

    oai_token-act-pair · gpt-3.5-turbo

    brand names and specific products within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    take
    -0.84
    editor
    -0.80
    table
    -0.77
    resist
    -0.77
    consider
    -0.76
    avoid
    -0.76
    duration
    -0.76
    Wil
    -0.75
    incent
    -0.75
    rab
    -0.75
    POSITIVE LOGITS
     Enterprises
    0.98
     Productions
    0.97
     Networks
    0.95
     Industries
    0.93
     Ventures
    0.91
    's
    0.91
     Group
    0.88
     Holdings
    0.86
     Express
    0.86
     Market
    0.85
    Activations Density 0.301%

    No Known Activations