© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1140
    Prev
    Next
    INDEX
    Explanations

    phrases related to reports and statements

    oai_token-act-pair · gpt-3.5-turbo

    punctuations and certain formats in the text, indicating sentence structure and reporting style

    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
     himself
    -0.78
     his
    -0.76
     pals
    -0.64
     unsus
    -0.64
     guy
    -0.63
     kid
    -0.62
     thrill
    -0.62
     fateful
    -0.60
     barg
    -0.60
     tornado
    -0.59
    POSITIVE LOGITS
    Its
    1.35
     Its
    1.19
    It
    1.05
    Specifically
    1.03
     It
    0.99
    emphasis
    0.98
    Recommend
    0.97
    Furthermore
    0.94
    its
    0.94
    Moreover
    0.91
    Activations Density 0.408%

    No Known Activations