© 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. 2-RES-JB
    11. 8001
    Prev
    Next
    INDEX
    Explanations

    phrases related to granting or providing access to something

    oai_token-act-pair · gpt-3.5-turbo

    references to access, particularly in legal, healthcare, and information contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    warm
    -0.66
    uke
    -0.64
     Fernand
    -0.62
    dylib
    -0.61
    pload
    -0.59
    hari
    -0.59
     Kern
    -0.58
     disband
    -0.58
     Gentle
    -0.58
    RNA
    -0.57
    POSITIVE LOGITS
    ibility
    1.16
    ilege
    1.00
    ibly
    0.99
     access
    0.98
    ibl
    0.97
    ãĥ¼ãĥĨ
    0.89
    ibles
    0.86
    ible
    0.86
    itud
    0.83
    access
    0.83
    Activations Density 0.028%

    No Known Activations