© 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. 6-RES-JB
    11. 3585
    Prev
    Next
    INDEX
    Explanations

    prepositions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate refusal or rejection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interchange
    -0.54
     accent
    -0.52
     crim
    -0.50
     cheers
    -0.50
    èĢħ
    -0.49
     accompanying
    -0.48
     corro
    -0.47
     deterior
    -0.47
     congratulate
    -0.45
     lia
    -0.45
    POSITIVE LOGITS
    ·
    0.63
    ©
    0.61
    ĩ
    0.59
    ī
    0.59
    ħ
    0.56
    orial
    0.55
    IJ
    0.54
    ĵĺ
    0.54
    °
    0.53
    ®
    0.53
    Activations Density 2.620%

    No Known Activations