© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6853
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative sentiments or criticism

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to "demeaning" or derogatory language

    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
     Elves
    -0.67
    tis
    -0.66
    heed
    -0.65
    ORY
    -0.64
    nce
    -0.63
     supper
    -0.62
    loo
    -0.61
    FORE
    -0.60
    Dub
    -0.60
     Hastings
    -0.60
    POSITIVE LOGITS
    agogue
    1.14
    igration
    1.04
    agog
    1.04
    aterial
    1.04
    ilit
    1.02
    ploy
    0.98
    ixed
    0.96
    otions
    0.96
    otion
    0.93
    ittance
    0.91
    Activations Density 0.018%

    No Known Activations