© 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. 9-RES-JB
    11. 17354
    Prev
    Next
    INDEX
    Explanations

    words related to potential risks and danger, especially in terms of legal consequences and physical harm

    oai_token-act-pair · gpt-3.5-turbo

    themes related to justice, fear, and the consequences of political actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.64
     ellipt
    -0.60
    angular
    -0.58
     neglected
    -0.56
    ellen
    -0.56
    ACTED
    -0.55
    ãĤ©
    -0.55
     complement
    -0.55
    dimension
    -0.53
    Balance
    -0.53
    POSITIVE LOGITS
     someday
    1.14
     repercussions
    0.96
     unless
    0.92
     if
    0.92
     retribution
    0.87
     anytime
    0.87
     tomorrow
    0.85
     wrath
    0.83
     repr
    0.82
    angering
    0.81
    Activations Density 0.368%

    No Known Activations