© 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. 4232
    Prev
    Next
    INDEX
    Explanations

    words related to emphasizing agreement or endorsement

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong opinions or endorsements

    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
     Corpse
    -0.71
     Parenthood
    -0.70
    ilage
    -0.69
    illions
    -0.67
     Miracle
    -0.67
     Gallery
    -0.67
     Thumbnails
    -0.66
    oleon
    -0.66
    acity
    -0.65
    emetery
    -0.65
    POSITIVE LOGITS
     discouraged
    0.97
     encouraged
    0.91
     disagree
    0.87
     discourage
    0.87
     advised
    0.85
     recommend
    0.84
     endorse
    0.84
     advocated
    0.82
     disliked
    0.81
     advise
    0.81
    Activations Density 0.038%

    No Known Activations