© 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. 21758
    Prev
    Next
    INDEX
    Explanations

    words related to legal and political terms, especially those related to rights and detention

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the" in various contexts

    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
    thood
    -0.80
     VIDEOS
    -0.76
     qualifies
    -0.75
    ieties
    -0.73
     besides
    -0.72
    mares
    -0.68
    rooms
    -0.67
     \(\
    -0.67
    cation
    -0.67
     strengthens
    -0.65
    POSITIVE LOGITS
     youngest
    1.18
     oldest
    1.17
     founder
    1.16
     president
    1.10
     eldest
    1.10
     former
    1.10
     mayor
    1.09
     deputy
    1.07
     chairman
    1.07
     director
    1.07
    Activations Density 0.108%

    No Known Activations