© 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. 10-RES-JB
    11. 13666
    Prev
    Next
    INDEX
    Explanations

    specific years or timeframes mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    specific historical and geographical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÃįÃį
    -0.79
    owship
    -0.65
    Ire
    -0.63
    plet
    -0.62
    omever
    -0.60
    Lear
    -0.59
    anding
    -0.58
    ÙĦ
    -0.58
    ¶æ
    -0.58
     therein
    -0.58
    POSITIVE LOGITS
     belongs
    0.94
     depends
    0.93
     varies
    0.93
     seems
    0.91
     consists
    0.91
     appears
    0.90
     contains
    0.89
     lasted
    0.89
     expires
    0.88
     explodes
    0.87
    Activations Density 0.525%

    No Known Activations