© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16902
    Prev
    Next
    INDEX
    Explanations

    mentions of software or computer client applications

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "client" in relation to software and applications

    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
    orie
    -0.97
    åħī
    -0.86
    borgh
    -0.76
    aurus
    -0.73
    utra
    -0.71
    ãĤ¼ãĤ¦ãĤ¹
    -0.70
    enda
    -0.69
    ãĥ©ãĥ³
    -0.69
    ĸļ
    -0.67
    rue
    -0.65
    POSITIVE LOGITS
    ele
    0.88
     implementations
    0.85
     software
    0.82
    Hello
    0.79
     side
    0.78
     SDK
    0.78
     runtime
    0.78
     client
    0.77
    Alias
    0.77
    client
    0.75
    Activations Density 0.034%

    No Known Activations