© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 21214
    Prev
    Next
    INDEX
    Explanations

    mentions of the existence or presence of people, entities, or things

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating location or existence of individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OWS
    -0.88
    advertising
    -0.70
    ĪĴ
    -0.68
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.66
    RESULTS
    -0.64
    omer
    -0.62
    ionage
    -0.61
    ãĤ´ãĥ³
    -0.61
    ãģķ
    -0.59
    20439
    -0.58
    POSITIVE LOGITS
     nowhere
    0.78
    abouts
    0.73
    itialized
    0.69
     here
    0.68
     waiting
    0.67
    clusions
    0.65
     somewhere
    0.65
     limbo
    0.63
     yours
    0.62
    oln
    0.61
    Activations Density 0.257%

    No Known Activations