© 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. 7-RES-JB
    11. 21635
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing an opinion or viewpoint

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "weigh in."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =]
    -0.78
    cia
    -0.66
    $$$$
    -0.60
    CLASSIFIED
    -0.59
     purposes
    -0.57
     Pegasus
    -0.54
    FK
    -0.54
    pelling
    -0.53
     reason
    -0.53
    lain
    -0.52
    POSITIVE LOGITS
    ordinate
    1.06
     unison
    0.87
     favour
    0.85
    clusions
    0.85
    between
    0.83
    effic
    0.81
    tical
    0.81
    animate
    0.80
    escap
    0.79
     accordance
    0.78
    Activations Density 0.097%

    No Known Activations