© 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. 20585
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussing or commenting on something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate decision-making and evaluative judgments

    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
    DragonMagazine
    -0.97
    ĸļ
    -0.78
    Ñĭ
    -0.77
    ridor
    -0.76
    etheless
    -0.76
    Ń·
    -0.76
    displayText
    -0.75
    mobi
    -0.73
    çīĪ
    -0.72
    externalActionCode
    -0.72
    POSITIVE LOGITS
     something
    1.34
     certain
    1.26
     anything
    1.23
     someone
    1.14
     things
    1.11
     decisions
    1.02
     unpopular
    1.01
     somebody
    1.01
     projects
    1.01
     situations
    0.98
    Activations Density 0.771%

    No Known Activations