© 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. 1-RES-JB
    11. 10314
    Prev
    Next
    INDEX
    Explanations

    phrases related to "Terminal" locations or concepts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Terminal" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gio
    -0.91
    FORE
    -0.81
    fulness
    -0.81
    iard
    -0.79
    hetti
    -0.78
    ork
    -0.77
    orth
    -0.75
    HL
    -0.73
    lier
    -0.72
    za
    -0.70
    POSITIVE LOGITS
     Terminal
    1.46
    Termin
    1.02
     terminal
    0.97
     terminals
    0.88
     satell
    0.80
    gments
    0.78
     tubes
    0.74
     mosqu
    0.71
     dumps
    0.70
     installations
    0.70
    Activations Density 0.007%

    No Known Activations