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. 6-RES-JB
    6. 21599
    Prev
    Next
    INDEX
    Explanations

    phrases related to the term "Access"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Access" and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stal
    -0.76
    pload
    -0.72
     sperm
    -0.64
    balls
    -0.64
    GGGG
    -0.62
     Sabha
    -0.62
     Fenrir
    -0.62
     prope
    -0.60
     strand
    -0.59
    nas
    -0.59
    POSITIVE LOGITS
    ibility
    1.47
    ible
    1.24
    ibles
    1.12
    ibly
    1.11
    ory
    0.99
    ibl
    0.96
    IBLE
    0.94
    ibilities
    0.90
    âĶģ
    0.86
    ilee
    0.80
    Activations Density 0.019%

    No Known Activations