© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3781
    Prev
    Next
    INDEX
    Explanations

    verbs related to political actions or decision-making, specifically with terms related to abstaining or shelving actions

    oai_token-act-pair · gpt-3.5-turbo
    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
     Inquis
    -0.71
     idiots
    -0.70
     imperfect
    -0.70
     precon
    -0.69
     frustrations
    -0.69
     hardships
    -0.69
     americ
    -0.68
    é¾įå¥ij士
    -0.67
     behavi
    -0.66
     deviations
    -0.66
    POSITIVE LOGITS
    osed
    1.27
    aled
    1.24
    ended
    1.21
    ved
    1.19
    ained
    1.17
    ached
    1.16
    azed
    1.15
    elled
    1.13
    uted
    1.13
    icated
    1.13
    Activations Density 0.174%

    No Known Activations