© 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. 6-RES-JB
    11. 2877
    Prev
    Next
    INDEX
    Explanations

    references to people or entities in brackets accompanied by some context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of brackets indicating quoted or referenced thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.81
    ĻĤ
    -0.80
    ĸļ
    -0.79
    ãĤ¶
    -0.73
    ãĥł
    -0.71
    aru
    -0.70
    Ń·
    -0.70
    -+-+
    -0.69
    İĭ
    -0.69
    zh
    -0.69
    POSITIVE LOGITS
    selves
    0.76
    },"
    0.68
    ."[
    0.62
    Management
    0.61
     Mol
    0.61
     waivers
    0.60
     Manifest
    0.60
     ,"
    0.57
     waiver
    0.56
    cape
    0.55
    Activations Density 0.077%

    No Known Activations