© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 11402
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters

    oai_token-act-pair · gpt-3.5-turbo

    assertive statements or claims regarding various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    »Ĵ
    -0.87
    izont
    -0.86
    rollers
    -0.85
    verning
    -0.85
    cycles
    -0.83
    ourning
    -0.82
    conservancy
    -0.82
    meric
    -0.80
    asters
    -0.80
    MpServer
    -0.80
    POSITIVE LOGITS
     assertion
    1.69
     statement
    1.51
     sentiment
    1.51
     remark
    1.46
     quote
    1.37
     notion
    1.37
     quotation
    1.36
     accusation
    1.35
     phrase
    1.33
     implication
    1.33
    Activations Density 0.330%

    No Known Activations