© 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. 4981
    Prev
    Next
    INDEX
    Explanations

    examples of phrases complementing someone's performance or work, such as 'outstanding job' or 'great job'

    oai_token-act-pair · gpt-3.5-turbo

    evaluative phrases related to the quality of performance

    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
     fears
    -0.69
    ONSORED
    -0.68
    fields
    -0.67
     Heard
    -0.66
     defeated
    -0.65
     Torn
    -0.65
    Magikarp
    -0.64
     Franch
    -0.64
     defended
    -0.64
    ildo
    -0.63
    POSITIVE LOGITS
     thing
    0.88
     homework
    0.86
     job
    0.83
     grunt
    0.82
     justice
    0.79
    pez
    0.77
     bidding
    0.76
     darn
    0.74
     deed
    0.74
     laundry
    0.73
    Activations Density 0.115%

    No Known Activations