© 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. 8-RES-JB
    11. 2014
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a sense of location or belonging related to a specific organization or community

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating location or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _>
    -0.77
     tyr
    -0.74
    emo
    -0.72
    imo
    -0.67
    _(
    -0.67
    />
    -0.65
    choice
    -0.65
    <?
    -0.63
    >(
    -0.63
    oldown
    -0.63
    POSITIVE LOGITS
    antage
    0.75
     ours
    0.70
     Trib
    0.69
     Arbor
    0.69
     DIY
    0.69
     Pot
    0.66
    ocated
    0.66
     HQ
    0.66
     Arlington
    0.65
     Appalach
    0.65
    Activations Density 0.148%

    No Known Activations