© 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. 10-RES-JB
    11. 703
    Prev
    Next
    INDEX
    Explanations

    words related to moral integrity or ethical violations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dishonesty and deception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Turks
    -0.66
     rhy
    -0.66
     Chick
    -0.65
     loose
    -0.62
     short
    -0.61
     pert
    -0.59
     Dutch
    -0.59
     Danish
    -0.59
     schizophrenia
    -0.59
     clay
    -0.59
    POSITIVE LOGITS
    ored
    2.05
    ors
    1.97
    oring
    1.86
    ours
    1.82
    ouring
    1.81
    oured
    1.81
    orship
    1.68
    our
    1.66
    orable
    1.59
    orous
    1.57
    Activations Density 0.073%

    No Known Activations