© 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. 2-RES-JB
    11. 19665
    Prev
    Next
    INDEX
    Explanations

    positive news and updates

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating positive news or good deals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Britann
    -0.77
     vans
    -0.76
    atars
    -0.76
     umb
    -0.74
     passports
    -0.71
    UA
    -0.70
    irez
    -0.70
     helicopters
    -0.70
     sacked
    -0.70
     invaded
    -0.68
    POSITIVE LOGITS
    âĦ¢:
    0.75
    feel
    0.69
    thank
    0.68
    nered
    0.68
    hander
    0.66
    \\\\\\\\
    0.66
     luck
    0.66
    please
    0.65
    getting
    0.65
    itiveness
    0.65
    Activations Density 1.155%

    No Known Activations