© 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. 3189
    Prev
    Next
    INDEX
    Explanations

    timestamps and dates

    oai_token-act-pair · gpt-3.5-turbo

    date and time information

    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
     Inher
    -0.68
    gem
    -0.63
     hemor
    -0.58
     unimagin
    -0.57
     misunder
    -0.56
     psychedel
    -0.56
     humble
    -0.55
     sponsoring
    -0.55
    ¬¼
    -0.54
     embryonic
    -0.54
    POSITIVE LOGITS
     GMT
    0.77
    UTC
    0.71
    atoes
    0.66
     2018
    0.66
    daq
    0.65
     accordingly
    0.64
     -->
    0.64
     TBD
    0.63
     URL
    0.63
     2017
    0.62
    Activations Density 0.023%

    No Known Activations