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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 14380
    Prev
    Next
    INDEX
    Explanations

    phrases related to instructions or directives

    oai_token-act-pair · gpt-3.5-turbo

    numerical symbols and coding representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Samar
    -0.66
    wagen
    -0.64
    itably
    -0.60
     Bermuda
    -0.57
     incent
    -0.55
     publicity
    -0.54
     staggered
    -0.54
     maxim
    -0.54
     donor
    -0.54
     Kenyan
    -0.53
    POSITIVE LOGITS
    ¹
    0.85
    £
    0.81
    bryce
    0.81
    Ī
    0.79
    âĹ¼
    0.78
    ¯
    0.77
    º
    0.75
    į
    0.75
    bol
    0.74
    §
    0.74
    Activations Density 0.481%

    No Known Activations