© 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. 8-RES-JB
    11. 3325
    Prev
    Next
    INDEX
    Explanations

    phrases related to critical analysis and intellectual engagement

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate moral judgment or critique regarding social and political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enery
    -0.69
    adelphia
    -0.65
    rete
    -0.64
     renovations
    -0.64
    icted
    -0.63
     XY
    -0.62
    Bang
    -0.61
     Rooms
    -0.60
    uberty
    -0.60
    apeake
    -0.60
    POSITIVE LOGITS
     cynicism
    1.09
     epist
    0.98
     disingen
    0.90
     rhetorical
    0.88
     hypocrisy
    0.87
     ideological
    0.86
     nihil
    0.83
     perverse
    0.82
     empir
    0.82
     counterproductive
    0.81
    Activations Density 1.324%

    No Known Activations