© 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. 7738
    Prev
    Next
    INDEX
    Explanations

    names of authors and the abbreviation 'et al' indicating multiple authors in a citation context

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific citations and authors

    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
    FactoryReloaded
    -0.76
     comprom
    -0.67
    CLASS
    -0.64
     Maker
    -0.63
    buster
    -0.63
     Advocate
    -0.63
     Username
    -0.63
     Corinth
    -0.61
     breaker
    -0.60
    adobe
    -0.60
    POSITIVE LOGITS
    .,
    1.38
    orporated
    0.94
    .;
    0.92
    .:
    0.92
    .,"
    0.89
    burgh
    0.85
    .?
    0.83
    ibi
    0.81
    inks
    0.80
    ogue
    0.79
    Activations Density 0.019%

    No Known Activations