© 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. 3-RES-JB
    11. 8732
    Prev
    Next
    INDEX
    Explanations

    legal and judgment-related terms such as "reasonable doubt" and "reasonable belief"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "reasonable" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chin
    -0.81
    yang
    -0.77
    Hop
    -0.73
    rio
    -0.73
     Tycoon
    -0.72
    fen
    -0.71
    cher
    -0.70
    sten
    -0.70
    along
    -0.70
    ept
    -0.69
    POSITIVE LOGITS
     accommodation
    0.89
     expectation
    0.88
     accommodations
    0.87
     sane
    0.84
     enough
    0.82
     bystanders
    0.79
     expectations
    0.78
     excuse
    0.78
     objections
    0.77
     explanations
    0.76
    Activations Density 0.013%

    No Known Activations