© 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. 6-RES-JB
    11. 8472
    Prev
    Next
    INDEX
    Explanations

    the term "harness" at varying strengths of activation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "harness" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estate
    -0.68
     accountant
    -0.68
     Currency
    -0.64
    acca
    -0.64
    onge
    -0.62
    cano
    -0.61
    away
    -0.61
    ahead
    -0.60
     Burnett
    -0.60
    chin
    -0.60
    POSITIVE LOGITS
    falls
    0.77
    ILLE
    0.76
    loo
    0.68
    vous
    0.68
    hou
    0.68
    ãĥ¯ãĥ³
    0.66
    ILS
    0.66
    raid
    0.65
    Viol
    0.65
    ught
    0.65
    Activations Density 0.050%

    No Known Activations