© 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. 10-RES-JB
    11. 4423
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences that contain the word "specifically."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĺħ
    -0.72
    ulton
    -0.68
    progress
    -0.68
     understandably
    -0.67
     Isles
    -0.67
     undoubtedly
    -0.67
     inevitably
    -0.66
     steadily
    -0.66
     predictably
    -0.66
    Progress
    -0.65
    POSITIVE LOGITS
     targeted
    0.95
     tailored
    0.91
     targeting
    0.90
     exempted
    0.89
     mention
    0.86
    ities
    0.84
     formulated
    0.81
     designed
    0.81
     mentions
    0.79
     mentioning
    0.78
    Activations Density 0.066%

    No Known Activations