© 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. 6-RES-JB
    11. 7902
    Prev
    Next
    INDEX
    Explanations

    references related to specific established entities, particularly Bard College

    oai_token-act-pair · gpt-3.5-turbo

    mentions of institutions and notable figures associated with academia or research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ressor
    -0.71
    ModLoader
    -0.71
    inance
    -0.68
    ĵĺ
    -0.68
    ends
    -0.68
    stakes
    -0.67
    Commerce
    -0.66
    rame
    -0.65
    ONG
    -0.65
     Luxem
    -0.64
    POSITIVE LOGITS
    sonian
    1.01
    llan
    0.87
    heim
    0.84
    isf
    0.80
    istic
    0.77
    obyl
    0.75
    ewater
    0.73
    ischer
    0.71
    gow
    0.71
    icial
    0.70
    Activations Density 0.065%

    No Known Activations