© 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. 11-RES-JB
    11. 1460
    Prev
    Next
    INDEX
    Explanations

    specific information or items within a category specified in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate conditions or specifications involving "that"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roots
    -0.74
    aign
    -0.65
    ãĤ´
    -0.64
    grim
    -0.61
    iots
    -0.60
    ahime
    -0.57
    bas
    -0.56
    enser
    -0.56
    ulz
    -0.55
    nin
    -0.55
    POSITIVE LOGITS
     deserve
    0.95
     could
    0.91
     might
    0.84
    could
    0.83
     merits
    0.83
     deserves
    0.81
     may
    0.80
     qualifies
    0.79
     merit
    0.78
    might
    0.76
    Activations Density 0.153%

    No Known Activations