© 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. 1-RES-JB
    11. 10281
    Prev
    Next
    INDEX
    Explanations

    references to relationships between individuals, especially in a collaborative or team setting

    oai_token-act-pair · gpt-3.5-turbo

    references to companionship or partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icer
    -0.82
    kefeller
    -0.82
    umbers
    -0.81
    IDER
    -0.71
    immer
    -0.70
    ghai
    -0.69
    ider
    -0.69
    icum
    -0.67
    umer
    -0.67
    amera
    -0.67
    POSITIVE LOGITS
    mates
    1.35
    mate
    1.34
     Swap
    0.74
     Delete
    0.72
    tenance
    0.71
     mate
    0.70
     Roc
    0.70
    volent
    0.70
    ysis
    0.68
    uates
    0.68
    Activations Density 0.010%

    No Known Activations