© 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. 19431
    Prev
    Next
    INDEX
    Explanations

    significant and impactful words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to strength, struggle, and complexity 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
     coh
    -0.66
     sugg
    -0.60
     jaw
    -0.59
     Kaf
    -0.58
    ãĥĩãĤ£
    -0.57
    PF
    -0.57
     Branch
    -0.57
     subp
    -0.57
     hypert
    -0.56
     captcha
    -0.56
    POSITIVE LOGITS
    !--
    0.88
    =-=-=-=-
    0.77
    nesses
    0.75
     ain
    0.71
    ness
    0.71
    hillary
    0.70
    erity
    0.68
     nonetheless
    0.68
    NESS
    0.66
     Indra
    0.66
    Activations Density 0.723%

    No Known Activations