© 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. 10-RES-JB
    11. 13945
    Prev
    Next
    INDEX
    Explanations

    acronyms and codes

    oai_token-act-pair · gpt-3.5-turbo

    acronyms or codes related to various organizations and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     awoken
    -0.79
    chers
    -0.69
    nces
    -0.67
    doors
    -0.64
    heimer
    -0.64
    wagen
    -0.62
     tion
    -0.61
    rers
    -0.60
    perse
    -0.60
    seeing
    -0.59
    POSITIVE LOGITS
    TN
    1.22
    RM
    1.22
    EB
    1.13
    Bs
    1.11
    P
    1.10
    CV
    1.10
    FW
    1.08
    RF
    1.08
    PB
    1.08
    AN
    1.08
    Activations Density 0.104%

    No Known Activations