© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 4617
    Prev
    Next
    INDEX
    Explanations

    terms related to termination, such as "terminated", "terminator", and "terminal"

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to termination or ending

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ered
    -0.82
    hari
    -0.82
    akening
    -0.77
    itsch
    -0.70
    resh
    -0.69
    lli
    -0.68
    yer
    -0.68
    hed
    -0.68
    htaking
    -0.68
    Ear
    -0.67
    POSITIVE LOGITS
     emulator
    0.90
     Termin
    0.75
    ology
    0.72
    termin
    0.71
    xes
    0.68
    thur
    0.68
    POS
    0.68
    fo
    0.66
     Velocity
    0.66
    idad
    0.66
    Activations Density 0.083%

    No Known Activations