© 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. 10-RES-JB
    11. 1095
    Prev
    Next
    INDEX
    Explanations

    phrases related to strong agreement or endorsement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating strong consensus or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    paces
    -0.91
    pace
    -0.89
    emis
    -0.85
    azine
    -0.85
    estyles
    -0.74
    cffff
    -0.74
    roups
    -0.71
    hift
    -0.69
    artments
    -0.69
    gered
    -0.68
    POSITIVE LOGITS
     rejection
    0.96
     YES
    0.90
     condemnation
    0.90
     refusal
    0.89
     negativity
    0.87
     dominance
    0.86
     majorities
    0.85
     affirmation
    0.82
     conviction
    0.81
     superiority
    0.81
    Activations Density 0.117%

    No Known Activations