Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 15792
    Prev
    Next
    INDEX
    Explanations

    words related to legal actions and individuals such as judges, lawyers, and criminals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of people

    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
    wolves
    -0.79
    region
    -0.69
    yrinth
    -0.68
    appropriate
    -0.67
    sequence
    -0.65
    ĭ
    -0.64
    ibilities
    -0.62
    Els
    -0.61
    requ
    -0.60
    obos
    -0.59
    POSITIVE LOGITS
     Sr
    1.07
     Jr
    0.94
     (@
    0.93
     attends
    0.90
     reacts
    0.89
     speaks
    0.84
     aka
    0.83
     Photographer
    0.82
     greets
    0.81
     poses
    0.80
    Activations Density 0.221%

    No Known Activations