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

    Neuronpedia

    Jacobian LensNEW
    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. 3844
    Prev
    Next
    INDEX
    Explanations

    phrases related to promotion or endorsing

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "promote" and its variations

    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
    quartered
    -0.79
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.71
    kes
    -0.67
    asso
    -0.67
    falls
    -0.65
    berg
    -0.65
    assian
    -0.65
    sbm
    -0.64
    nery
    -0.63
    quarters
    -0.62
    POSITIVE LOGITS
    entious
    0.84
     abstinence
    0.79
     awareness
    0.79
    ably
    0.78
     excellence
    0.78
    inently
    0.77
     entrepreneurship
    0.77
    andise
    0.77
     democracy
    0.77
     intolerance
    0.75
    Activations Density 0.076%

    No Known Activations