© 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. 1-RES-JB
    11. 3626
    Prev
    Next
    INDEX
    Explanations

    words associated with technology, such as code, script, and email

    oai_token-act-pair · gpt-3.5-turbo

    specific entities or brands in entertainment and art references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arsity
    -0.56
    ãĥ¼ãĥĨãĤ£
    -0.54
    ãĥ¼ãĥĨ
    -0.54
     Aure
    -0.52
    mx
    -0.52
    代
    -0.50
    ãĤ´ãĥ³
    -0.47
    ãĤ¦ãĤ¹
    -0.47
    Loading
    -0.46
    055
    -0.46
    POSITIVE LOGITS
    bard
    0.49
    NetMessage
    0.49
    etheless
    0.48
    hern
    0.48
    lly
    0.47
    MpServer
    0.46
    ongyang
    0.46
    NRS
    0.45
     exting
    0.44
    IRE
    0.44
    Activations Density 4.087%

    No Known Activations