© 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. 4-RES-JB
    11. 7259
    Prev
    Next
    INDEX
    Explanations

    legal or authoritative terms and language

    oai_token-act-pair · gpt-3.5-turbo

    the term "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 @ 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
    berman
    -0.74
    inis
    -0.73
    along
    -0.71
    fen
    -0.70
    rey
    -0.68
    chin
    -0.67
    uality
    -0.67
    tha
    -0.67
    jong
    -0.66
    yang
    -0.65
    POSITIVE LOGITS
     expectation
    0.85
     sane
    0.84
     accommodations
    0.82
     accommodation
    0.79
     priced
    0.78
     expectations
    0.77
     amounts
    0.77
     sized
    0.74
     guesses
    0.74
     reasonable
    0.72
    Activations Density 0.020%

    No Known Activations