Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 10770
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "access" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to the concept of "access" to various resources or information

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kern
    -0.78
     farewell
    -0.64
     almond
    -0.62
     Opera
    -0.61
    Maker
    -0.60
     disband
    -0.57
     Saud
    -0.56
     condol
    -0.55
     candle
    -0.55
    annis
    -0.54
    POSITIVE LOGITS
    ibility
    1.38
    ibly
    1.25
    ible
    1.17
    ioned
    1.01
    ibilities
    0.98
    ion
    0.97
    ãĥ¼ãĥĨ
    0.95
    ibl
    0.93
    ibles
    0.90
    ory
    0.83
    Activations Density 0.024%

    No Known Activations