© 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. 1-RES-JB
    11. 18672
    Prev
    Next
    INDEX
    Explanations

    keywords related to gaining unauthorized entry or possession, whether physical or digital

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "access" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Crus
    -0.73
    riot
    -0.67
     rabbits
    -0.65
    heartedly
    -0.64
    neg
    -0.64
     devils
    -0.64
    gas
    -0.63
     coat
    -0.63
     dust
    -0.59
    board
    -0.59
    POSITIVE LOGITS
     Accessed
    1.14
     accessed
    1.00
    CLASSIFIED
    0.97
    ibility
    0.94
    éĹĺ
    0.87
    ãĤ¯
    0.84
    Initialized
    0.83
    terday
    0.83
    æĸ¹
    0.83
    >]
    0.81
    Activations Density 0.003%

    No Known Activations