© 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. 11-RES-JB
    11. 22457
    Prev
    Next
    INDEX
    Explanations

    phrases related to reviewing and altering systems or processes

    oai_token-act-pair · gpt-3.5-turbo

    references to changes or reforms in systems or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     raping
    -0.67
     murders
    -0.64
     murdering
    -0.63
     kills
    -0.62
     sexually
    -0.62
     partying
    -0.61
     KILL
    -0.61
     mates
    -0.61
     killers
    -0.61
     virginity
    -0.61
    POSITIVE LOGITS
    ascript
    0.95
    enary
    0.73
    agraph
    0.68
    ciplinary
    0.68
    actionDate
    0.68
    FAQ
    0.68
    andum
    0.67
    disciplinary
    0.65
    soType
    0.65
    alan
    0.65
    Activations Density 0.811%

    No Known Activations