© 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. 9975
    Prev
    Next
    INDEX
    Explanations

    phrases related to intention or purpose

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating purpose or intent

    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
    listed
    -0.66
     choosing
    -0.64
     Forced
    -0.64
    Got
    -0.62
     knots
    -0.62
    standing
    -0.61
    hot
    -0.60
     Wicked
    -0.60
     Appears
    -0.60
     minded
    -0.58
    POSITIVE LOGITS
     stimulate
    1.34
     alleviate
    1.28
     promote
    1.25
     elicit
    1.25
     facilitate
    1.24
     discourage
    1.21
     encourage
    1.21
     emulate
    1.20
     counteract
    1.20
     simulate
    1.20
    Activations Density 0.175%

    No Known Activations