© 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. 9-RES-JB
    11. 13414
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings and social issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to obstacles or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shown
    -0.91
    Additionally
    -0.86
     Whilst
    -0.84
    Following
    -0.84
    Furthermore
    -0.82
    icipated
    -0.80
    However
    -0.77
     Additionally
    -0.74
    respective
    -0.73
     behaviours
    -0.73
    POSITIVE LOGITS
     godd
    0.88
     lousy
    0.87
     goddamn
    0.81
     ain
    0.81
     crappy
    0.79
     stupid
    0.77
     Godd
    0.75
     everywhere
    0.75
     dude
    0.74
     guy
    0.72
    Activations Density 1.794%

    No Known Activations