© 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. 15722
    Prev
    Next
    INDEX
    Explanations

    words related to administrative actions or proceedings

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "ad."

    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
     shorth
    -0.72
    Jr
    -0.65
     Weir
    -0.63
     Kafka
    -0.62
     wound
    -0.61
     pains
    -0.59
     SOC
    -0.59
    ãĥīãĥ©ãĤ´ãĥ³
    -0.57
     clearance
    -0.57
     Jenner
    -0.56
    POSITIVE LOGITS
    ventures
    1.68
    vance
    1.60
    venture
    1.59
    voc
    1.44
    vertis
    1.43
    ults
    1.40
    mittedly
    1.40
    olescent
    1.36
    visors
    1.28
    hesive
    1.27
    Activations Density 0.021%

    No Known Activations