© 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. 23242
    Prev
    Next
    INDEX
    Explanations

    words related to significant events or serious topics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to moral and ethical concepts, particularly in the context of human dignity and social issues

    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
    boro
    -0.65
    bell
    -0.62
    cham
    -0.57
    BOOK
    -0.56
    hook
    -0.56
     âĨij
    -0.54
    liquid
    -0.53
    kick
    -0.53
    ĵĺ
    -0.53
     Twice
    -0.53
    POSITIVE LOGITS
    ity
    3.62
    ities
    2.78
    ITY
    2.23
    itous
    1.99
    ité
    1.95
    ITIES
    1.93
    itarian
    1.65
    ties
    1.44
    idad
    1.38
    itas
    1.37
    Activations Density 0.195%

    No Known Activations