© 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. 23832
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or changes involving social, political, or economic matters

    oai_token-act-pair · gpt-3.5-turbo

    references to societal issues and discussions surrounding solutions

    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
    edin
    -0.66
    ocy
    -0.65
    âĵĺ
    -0.65
     âĵĺ
    -0.65
    urations
    -0.64
    heet
    -0.63
    sburgh
    -0.63
     ([
    -0.63
    roth
    -0.61
    MpServer
    -0.60
    POSITIVE LOGITS
     which
    1.00
    which
    0.99
     whose
    0.94
     whom
    0.85
    whose
    0.84
     equivalent
    0.81
     notwithstanding
    0.80
    arently
    0.77
    nown
    0.76
     arguably
    0.76
    Activations Density 0.855%

    No Known Activations