© 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. 5892
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an action or effort being made to achieve a specific goal

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating efforts or attempts to achieve something

    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
     Regions
    -0.67
     Charges
    -0.63
     Authors
    -0.63
     Errors
    -0.61
     Gloves
    -0.60
     Runes
    -0.60
     Consider
    -0.60
     Sear
    -0.60
     Frag
    -0.59
     Elements
    -0.59
    POSITIVE LOGITS
    PsyNetMessage
    0.78
    wark
    0.77
     appease
    0.69
    ãĥ¬
    0.69
    ipal
    0.68
    ãĤ¬
    0.68
    ãĥ¼ãĤ¯
    0.68
     reversal
    0.68
    finder
    0.67
     to
    0.67
    Activations Density 0.051%

    No Known Activations