© 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. 4-RES-JB
    11. 6076
    Prev
    Next
    INDEX
    Explanations

    information related to media releases like music albums, movies, and TV shows

    oai_token-act-pair · gpt-3.5-turbo

    references to new releases and updates in the entertainment industry

    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
    insured
    -0.62
     (âĪĴ
    -0.62
     subsistence
    -0.60
     complying
    -0.60
     labour
    -0.59
     phosphorus
    -0.57
     employers
    -0.56
     welfare
    -0.56
     Applicant
    -0.56
    independence
    -0.55
    POSITIVE LOGITS
     premie
    0.81
     cinematic
    0.79
     soundtrack
    0.76
     premiered
    0.76
     Cartoon
    0.75
     comedic
    0.75
     premiere
    0.74
     previews
    0.73
     Comedy
    0.73
     hilar
    0.72
    Activations Density 3.027%

    No Known Activations