© 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. 10-RES-JB
    11. 4385
    Prev
    Next
    INDEX
    Explanations

    phrases related to different types of technical specifications or products such as model numbers and names

    oai_token-act-pair · gpt-3.5-turbo

    references to high-tech military or aviation equipment

    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
    orious
    -0.76
    enhagen
    -0.76
    chers
    -0.76
    fman
    -0.76
    bats
    -0.76
    eering
    -0.73
    iful
    -0.70
    orius
    -0.67
    odore
    -0.66
    umo
    -0.65
    POSITIVE LOGITS
    ospital
    1.22
    OST
    1.12
    ancock
    1.10
    BP
    1.05
    arrison
    0.99
    azard
    0.99
    awk
    0.98
    awks
    0.98
    IGH
    0.97
    ERE
    0.96
    Activations Density 0.062%

    No Known Activations