© 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. 7747
    Prev
    Next
    INDEX
    Explanations

    keywords associated with gaining entry or permission to something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of access to information or resources

    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
     Kern
    -0.83
     farewell
    -0.64
     Jou
    -0.63
     occurrence
    -0.57
    Maker
    -0.57
     1895
    -0.57
     Inher
    -0.56
     almond
    -0.56
     1893
    -0.55
     invention
    -0.55
    POSITIVE LOGITS
    ibility
    1.29
    ibly
    1.29
    ible
    1.14
    ioned
    1.01
     thereto
    0.99
    ibilities
    0.95
    ion
    0.88
    ibl
    0.87
    ibles
    0.86
    ãĥ¼ãĥĨ
    0.86
    Activations Density 0.030%

    No Known Activations