© 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. 8-RES-JB
    11. 22298
    Prev
    Next
    INDEX
    Explanations

    phrases related to permissions or restrictions on the use of content

    oai_token-act-pair · gpt-3.5-turbo

    terms related to content restriction and redistribution policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gone
    -0.80
    ties
    -0.74
    chall
    -0.73
    wear
    -0.68
    lif
    -0.67
    test
    -0.67
    building
    -0.67
    surv
    -0.66
    tail
    -0.65
    burning
    -0.65
    POSITIVE LOGITS
     IMAGES
    0.85
     redistributed
    0.80
     Vaugh
    0.76
     Franch
    0.73
    arnaev
    0.68
    ONSORED
    0.67
     Fei
    0.67
     PHOTO
    0.66
    imate
    0.65
     ILCS
    0.64
    Activations Density 0.021%

    No Known Activations