© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 2751
    Prev
    Next
    INDEX
    Explanations

    legal or justice-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to legal terms or courtroom proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocene
    -0.61
     ..........
    -0.59
    fecture
    -0.59
    osion
    -0.59
    iesta
    -0.57
    ãĤ¼ãĤ¦ãĤ¹
    -0.57
    ::::::::
    -0.57
    ahime
    -0.56
    ongevity
    -0.56
    anguages
    -0.56
    POSITIVE LOGITS
     furthermore
    0.98
    sequently
    0.88
     stated
    0.87
     subsequently
    0.85
     implication
    0.85
     moreover
    0.84
     therefore
    0.84
     asserted
    0.84
     latter
    0.84
     cited
    0.81
    Activations Density 1.107%

    No Known Activations