© 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. 11-RES-JB
    11. 24443
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific names

    oai_token-act-pair · gpt-3.5-turbo

    definite articles, indicating a focus on specific entities or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ADE
    -0.74
    å·
    -0.71
    Ïī
    -0.66
    watching
    -0.65
    existent
    -0.64
    estern
    -0.63
    bane
    -0.63
     âĢº
    -0.62
    acet
    -0.62
    ãĥīãĥ©
    -0.62
    POSITIVE LOGITS
     remainder
    1.71
     rest
    1.54
     remaining
    1.51
     others
    1.46
     latter
    1.21
     youngest
    1.20
    oret
    1.17
     Others
    1.13
     oldest
    1.07
     other
    1.05
    Activations Density 0.318%

    No Known Activations