© 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. 14253
    Prev
    Next
    INDEX
    Explanations

    names of specific places or organizations, particularly ones related to legal proceedings or geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    names of people and places

    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
     conversion
    -0.76
    eger
    -0.72
    verty
    -0.66
    esa
    -0.66
    washing
    -0.65
    chio
    -0.64
     functioning
    -0.64
     grate
    -0.64
     eyebrow
    -0.63
    rans
    -0.62
    POSITIVE LOGITS
     Nass
    1.04
    amus
    0.99
     Vie
    0.75
    idia
    0.74
    asonic
    0.73
     Ferr
    0.73
    aceae
    0.72
    irgin
    0.72
    abis
    0.71
    ula
    0.71
    Activations Density 0.014%

    No Known Activations