© 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. 9-RES-JB
    11. 15600
    Prev
    Next
    INDEX
    Explanations

    phrases indicating statements or opinions

    oai_token-act-pair · gpt-3.5-turbo

    frequent use of personal pronouns and subjective expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    .</
    -0.71
    ãĢĤ
    -0.67
    .}
    -0.66
    .(
    -0.61
     �
    -0.60
    ////
    -0.60
    ãĢij
    -0.60
    .<
    -0.58
    âĢ¢âĢ¢
    -0.58
     -->
    -0.58
    POSITIVE LOGITS
    zbollah
    1.01
    odore
    0.90
    ffield
    0.89
    xiety
    0.87
    vana
    0.85
     certainly
    0.85
    usterity
    0.84
     definitely
    0.82
    %"
    0.82
    pherd
    0.82
    Activations Density 0.254%

    No Known Activations