© 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. 4-RES-JB
    11. 10316
    Prev
    Next
    INDEX
    Explanations

    terms related to advertising and promotional content

    oai_token-act-pair · gpt-3.5-turbo

    elements related to advertising and promotional content

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

    No Comments

    Negative Logits
    elsen
    -0.86
    uncture
    -0.76
    cffff
    -0.71
    cible
    -0.70
     culp
    -0.69
    ationally
    -0.68
    immune
    -0.67
    iciary
    -0.67
    ãĤ¦ãĤ¹
    -0.65
    chwitz
    -0.65
    POSITIVE LOGITS
     titled
    0.90
    vertisement
    0.84
     featuring
    0.81
     headlined
    0.80
     summar
    0.78
     entitled
    0.77
     advertisement
    0.76
    strip
    0.76
     infographic
    0.74
     flyer
    0.73
    Activations Density 0.368%

    No Known Activations