© 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. 3-RES-JB
    11. 7138
    Prev
    Next
    INDEX
    Explanations

    words related to J.R.R. Tolkien and his works like "Middle Earth," "Hobbit," and "Rings."

    oai_token-act-pair · gpt-3.5-turbo

    references to the works and characters of J.R.R. Tolkien

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aminer
    -0.84
    aple
    -0.71
    erve
    -0.69
    ħ
    -0.68
    apse
    -0.68
    apsed
    -0.67
    packages
    -0.67
    iments
    -0.66
    isting
    -0.66
    fficiency
    -0.66
    POSITIVE LOGITS
    olkien
    1.40
     Tolkien
    1.24
     Hobbit
    1.03
    sson
    1.03
     Gand
    0.96
     trilogy
    0.81
     Lann
    0.79
     Jinn
    0.69
     Andersen
    0.69
     Bagg
    0.68
    Activations Density 0.013%

    No Known Activations