© 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. 13622
    Prev
    Next
    INDEX
    Explanations

    the word "Dist" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "distribute" or related terms

    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
    glers
    -1.17
    swick
    -0.93
    terday
    -0.86
    ppo
    -0.83
    tes
    -0.79
    fter
    -0.70
    gery
    -0.70
    ton
    -0.70
    theless
    -0.69
    ggle
    -0.68
    POSITIVE LOGITS
    ribut
    1.42
    ributed
    1.41
    ribute
    1.23
    ribution
    1.22
    illery
    1.20
    inguished
    1.19
    ortion
    1.14
    rict
    1.11
    inctions
    1.06
    inct
    1.04
    Activations Density 0.013%

    No Known Activations