© 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. 6-RES-JB
    11. 17418
    Prev
    Next
    INDEX
    Explanations

    adjectives or phrases related to correctness or appropriateness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "appropriate" and its context in relation to behavior or actions

    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
    chet
    -0.87
    plane
    -0.79
    planes
    -0.78
    glass
    -0.78
    urger
    -0.77
    cher
    -0.76
    ker
    -0.75
    cipl
    -0.74
    stead
    -0.73
    peak
    -0.73
    POSITIVE LOGITS
    tarian
    0.85
     punishment
    0.84
     Dragonbound
    0.83
     circumstances
    0.82
     punishments
    0.80
     amounts
    0.80
     sized
    0.78
     responses
    0.78
    appropriate
    0.76
     attire
    0.74
    Activations Density 0.030%

    No Known Activations