© 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. 4-RES-JB
    11. 392
    Prev
    Next
    INDEX
    Explanations

    legal and investigative terminology related to establishing a justifiable reason for actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to probability and presumption

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

    No Comments

    Negative Logits
    erie
    -0.94
    ebook
    -0.85
    eteria
    -0.82
    ffield
    -0.80
    arling
    -0.78
    hetti
    -0.78
    ophon
    -0.76
    icky
    -0.75
    ithing
    -0.74
    uden
    -0.74
    POSITIVE LOGITS
     warrant
    0.82
     warrants
    0.81
     cause
    0.80
     probable
    0.79
     indication
    0.77
     unbeliev
    0.72
     disposition
    0.72
    itial
    0.71
     affidavit
    0.71
     suspect
    0.71
    Activations Density 0.012%

    No Known Activations