© 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. 20622
    Prev
    Next
    INDEX
    Explanations

    phrases related to questions or prompts

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods and question marks

    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
    jri
    -0.77
    vertisement
    -0.75
     extingu
    -0.70
     phased
    -0.69
     glim
    -0.68
     purch
    -0.67
     bounded
    -0.67
     confir
    -0.67
    tera
    -0.66
     satell
    -0.66
    POSITIVE LOGITS
     Lastly
    2.09
     Finally
    1.98
     These
    1.58
     Both
    1.58
     Whatever
    1.53
    Finally
    1.53
    Lastly
    1.48
     Together
    1.46
    etc
    1.41
    These
    1.40
    Activations Density 0.441%

    No Known Activations