© 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. 8-RES-JB
    11. 4900
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to technology and industry partnerships

    oai_token-act-pair · gpt-3.5-turbo

    terms related to shared technology and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izabeth
    -0.68
     congr
    -0.67
     Went
    -0.62
     whiff
    -0.56
     Shelley
    -0.56
     ..."
    -0.56
    ERSON
    -0.56
    ************
    -0.56
     playbook
    -0.55
    UFC
    -0.55
    POSITIVE LOGITS
     refers
    0.97
     consists
    0.94
     involves
    0.86
    inarily
    0.83
     denotes
    0.83
     differs
    0.80
     represents
    0.80
     occurs
    0.77
     Basics
    0.77
    ization
    0.76
    Activations Density 0.389%

    No Known Activations