© 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. 7-RES-JB
    11. 12592
    Prev
    Next
    INDEX
    Explanations

    commands and instructions related to software development

    oai_token-act-pair · gpt-3.5-turbo

    sequences or phrases typically found in technical or instructional writing

    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
    ŃĶ
    -0.62
    ismo
    -0.62
     convictions
    -0.60
    ideon
    -0.59
     eminent
    -0.59
    enance
    -0.59
    rica
    -0.58
     boycot
    -0.58
    levision
    -0.57
    stru
    -0.57
    POSITIVE LOGITS
     namely
    1.15
     preferably
    1.11
     please
    1.04
     ie
    1.03
     however
    0.99
     aka
    0.96
     etc
    0.96
     optionally
    0.92
     PLEASE
    0.92
    yip
    0.90
    Activations Density 0.479%

    No Known Activations