© 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. 9945
    Prev
    Next
    INDEX
    Explanations

    phrases related to business and commerce

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "The" and variations in context

    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
    soType
    -0.80
     beforehand
    -0.79
    Prosecut
    -0.77
    Ò
    -0.76
     according
    -0.74
    estamp
    -0.72
    ilee
    -0.70
    plet
    -0.69
    rade
    -0.68
    thood
    -0.68
    POSITIVE LOGITS
     result
    1.16
    oret
    1.15
     downside
    1.09
     sheer
    1.03
     irony
    1.02
     exception
    1.01
    ories
    1.00
     possibilities
    1.00
     simplest
    1.00
     exceptions
    0.99
    Activations Density 0.259%

    No Known Activations