© 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. 11-RES-JB
    11. 14589
    Prev
    Next
    INDEX
    Explanations

    instances of the special character 'Ċ'

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or metrics related to various topics

    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
     crocod
    -0.86
     oun
    -0.84
     square
    -0.80
     buoy
    -0.78
     Mub
    -0.78
     sacrific
    -0.77
     nerv
    -0.76
     Shia
    -0.76
     chant
    -0.75
     spitting
    -0.75
    POSITIVE LOGITS
    Reviewer
    1.44
    Page
    1.42
    matter
    1.37
    âĹ¼
    1.36
    enough
    1.33
    together
    1.32
    appropriate
    1.32
    acqu
    1.32
    accompan
    1.31
    said
    1.31
    Activations Density 0.143%

    No Known Activations