© 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. 21206
    Prev
    Next
    INDEX
    Explanations

    text related to user interaction and friendliness in technology contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with user-generated content and user experience

    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
    ĪĴ
    -0.78
     knots
    -0.77
    ulhu
    -0.75
    rontal
    -0.68
     veins
    -0.67
    ioxide
    -0.64
    enegger
    -0.64
    女
    -0.62
    ŃĶ
    -0.61
    elia
    -0.61
    POSITIVE LOGITS
    upload
    0.76
    utters
    0.71
    facing
    0.70
    iscons
    0.69
    friendly
    0.69
     EQ
    0.68
     guides
    0.68
    reciation
    0.67
     Ratings
    0.67
    guide
    0.65
    Activations Density 0.255%

    No Known Activations