© 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 EvalsExportsinterp-engineNEWAPI 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. 7249
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences where someone is actively participating or engaging in an activity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "take part in" in various contexts

    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
    uncle
    -0.75
    glass
    -0.72
    mother
    -0.72
    iola
    -0.72
    pter
    -0.68
    isphere
    -0.67
    enders
    -0.66
    named
    -0.65
    father
    -0.64
    ren
    -0.64
    POSITIVE LOGITS
     hostilities
    1.01
     negotiations
    0.95
     discussions
    0.94
     ceremonies
    0.89
     deliberations
    0.86
     trials
    0.83
     shaping
    0.83
     festivities
    0.83
     conversation
    0.83
     conversations
    0.81
    Activations Density 0.130%

    No Known Activations