© 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. 7-RES-JB
    11. 2158
    Prev
    Next
    INDEX
    Explanations

    instances of people meeting or interacting with others or being in specific locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of people meeting or interacting with others in specific contexts or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Laksh
    -0.74
     replaced
    -0.70
    FIG
    -0.70
     Included
    -0.65
     substituted
    -0.64
     awaits
    -0.63
    ieties
    -0.62
    itized
    -0.62
    Reviewed
    -0.62
    iod
    -0.59
    POSITIVE LOGITS
    oba
    0.84
    brother
    0.70
    apixel
    0.64
     advoc
    0.64
     whom
    0.62
    assad
    0.62
    illac
    0.62
     friendship
    0.62
     bluff
    0.61
     caravan
    0.61
    Activations Density 0.536%

    No Known Activations