© 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. 9-RES-JB
    11. 16281
    Prev
    Next
    INDEX
    Explanations

    names of legal documents

    oai_token-act-pair · gpt-3.5-turbo

    markers for sections or formatting in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĸ¬
    -0.72
    keeper
    -0.70
    âĸ¬âĸ¬
    -0.64
    ãĥ£
    -0.63
     convict
    -0.63
    stro
    -0.62
    bal
    -0.61
    bing
    -0.59
    ++++++++++++++++
    -0.59
     CONTROL
    -0.59
    POSITIVE LOGITS
    atinum
    1.49
    enty
    1.48
    asma
    1.45
    utonium
    1.26
    anned
    1.22
    ague
    1.17
    ausible
    1.16
    acement
    1.11
    umbers
    1.08
    astic
    1.07
    Activations Density 0.035%

    No Known Activations