© 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. 2521
    Prev
    Next
    INDEX
    Explanations

    words related to hydration and hydropower

    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
    ãģį
    -0.77
    ãģĦ
    -0.69
     Borough
    -0.69
     Osw
    -0.68
    istically
    -0.67
     Mutual
    -0.65
     nomine
    -0.64
    ourning
    -0.63
    éĹĺ
    -0.62
    */(
    -0.62
    POSITIVE LOGITS
    ration
    1.32
    rolog
    1.31
    rox
    1.20
    rated
    1.19
    roph
    1.17
    rol
    1.17
    rogen
    1.16
    rating
    1.12
    rology
    1.08
    rog
    1.08
    Activations Density 0.044%

    No Known Activations