© 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. 24311
    Prev
    Next
    INDEX
    Explanations

    references to transparency and honesty

    oai_token-act-pair · gpt-3.5-turbo

    terms related to transparency

    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
    req
    -0.82
    skill
    -0.76
    ander
    -0.73
    Fan
    -0.70
    ucky
    -0.70
    Stars
    -0.69
    AMI
    -0.69
    ATCH
    -0.68
    otos
    -0.67
    iddling
    -0.65
    POSITIVE LOGITS
     transparent
    1.12
    ly
    0.99
    ible
    0.95
    iary
    0.89
    parency
    0.89
     opaque
    0.84
    idious
    0.83
    ibility
    0.81
     transparency
    0.79
    ibly
    0.79
    Activations Density 0.011%

    No Known Activations