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. 20994
    Prev
    Next
    INDEX
    Explanations

    medical conditions, legal terms, and various technical details

    oai_token-act-pair · gpt-3.5-turbo

    topics related to health and medical conditions

    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
     alike
    -0.73
     Motorsport
    -0.61
     COMPLE
    -0.61
     Multiplayer
    -0.60
    rawdownloadcloneembedreportprint
    -0.59
    iolet
    -0.59
     independ
    -0.59
     ______
    -0.58
    ³³³³
    -0.58
     eg
    -0.58
    POSITIVE LOGITS
     prank
    0.84
     ploy
    0.81
     loophole
    0.81
     allegation
    0.81
     debacle
    0.79
     fiasco
    0.79
     lawsuit
    0.76
     controversy
    0.73
     violation
    0.73
     bracelet
    0.72
    Activations Density 0.602%

    No Known Activations