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

    Neuronpedia

    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. 7902
    Prev
    Next
    INDEX
    Explanations

    adjectives related to value or magnitude

    oai_token-act-pair · gpt-3.5-turbo

    text related to legal or procedural terms

    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
    Published
    -0.58
    ï¸
    -0.58
    \",
    -0.57
    veland
    -0.55
     although
    -0.55
     Belfast
    -0.55
     Shutterstock
    -0.54
     Published
    -0.53
    EEE
    -0.53
     POLIT
    -0.52
    POSITIVE LOGITS
    anooga
    0.82
     becomes
    0.81
     persists
    0.72
     remains
    0.72
     overwhel
    0.70
     remained
    0.69
     thereof
    0.69
    itiz
    0.68
     tends
    0.67
     seems
    0.65
    Activations Density 1.474%

    No Known Activations