© 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. 9-RES-JB
    11. 18409
    Prev
    Next
    INDEX
    Explanations

    sentences with dashes

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Elys
    -0.67
     Slug
    -0.65
     Borders
    -0.62
     messenger
    -0.62
     Paso
    -0.61
     Camel
    -0.60
     Dragons
    -0.58
     Rhod
    -0.57
     Returns
    -0.57
     Balanced
    -0.57
    POSITIVE LOGITS
     gasp
    1.16
    again
    1.13
    albeit
    1.12
    perhaps
    1.05
    almost
    1.00
    quite
    0.99
    surprisingly
    0.91
    successfully
    0.91
    according
    0.90
    along
    0.89
    Activations Density 0.124%

    No Known Activations