© 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. 20257
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "fake"

    oai_token-act-pair · gpt-3.5-turbo

    references to "fake news."

    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
    xual
    -0.90
    arching
    -0.80
    riott
    -0.78
    onen
    -0.76
    hem
    -0.73
     guiActiveUnfocused
    -0.73
    ands
    -0.70
    azard
    -0.68
    bard
    -0.68
    pour
    -0.68
    POSITIVE LOGITS
    ument
    0.98
     pas
    0.87
     IDs
    0.84
     news
    0.76
     positives
    0.74
    ulent
    0.73
     tan
    0.71
    ulously
    0.69
     sounding
    0.67
     identities
    0.65
    Activations Density 0.070%

    No Known Activations