© 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 EvalsExportsinterp-engineNEWAPI 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. 1112
    Prev
    Next
    INDEX
    Explanations

    mentions of media personalities and news events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the special character 'âĢ'

    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
    anwhile
    -0.72
     segreg
    -0.61
     Sic
    -0.60
     Franch
    -0.58
     scattering
    -0.57
     Constantin
    -0.57
     psychiat
    -0.57
     Afric
    -0.56
     Mous
    -0.56
     Tanz
    -0.56
    POSITIVE LOGITS
    ¬
    1.13
    ľ
    1.13
    Ń
    1.02
    Ķ
    0.97
    ¦
    0.96
    ¡
    0.96
    ĺ
    0.95
    º
    0.95
    £
    0.93
    ķ
    0.92
    Activations Density 0.308%

    No Known Activations