© 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. 6-RES-JB
    11. 3091
    Prev
    Next
    INDEX
    Explanations

    references to interviews, blog posts, and written statements

    oai_token-act-pair · gpt-3.5-turbo

    content that references reports, posts, and interviews

    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
     Sabha
    -0.66
    BUG
    -0.62
    asus
    -0.62
    complex
    -0.58
     Ultron
    -0.58
    INAL
    -0.58
    TYPE
    -0.57
    osi
    -0.57
     Stability
    -0.57
     ESA
    -0.56
    POSITIVE LOGITS
    uggest
    1.30
    mith
    1.26
    creen
    1.24
    hips
    1.20
    poons
    1.11
    ettings
    1.10
    hops
    1.10
    pring
    1.08
    chool
    1.08
    hip
    1.06
    Activations Density 0.183%

    No Known Activations