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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 24064
    Prev
    Next
    INDEX
    Explanations

    terms related to gathering or collecting information or data

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gathering and analyzing information or data

    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
     Carbuncle
    -0.65
     rejoice
    -0.65
    ocker
    -0.64
    Hop
    -0.62
     Trilogy
    -0.59
    axis
    -0.57
     beware
    -0.56
    aughs
    -0.56
    xtap
    -0.55
     Cancel
    -0.54
    POSITIVE LOGITS
     about
    1.48
     regarding
    1.41
     pertaining
    1.29
     relating
    1.29
     concerning
    1.27
     ABOUT
    1.20
     detailing
    1.14
    about
    1.10
     related
    0.99
     About
    0.97
    Activations Density 0.281%

    No Known Activations