© 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. 7-RES-JB
    11. 13423
    Prev
    Next
    INDEX
    Explanations

    references to software updates and system prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    terms related to software development and programming commands

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vows
    -0.74
     wills
    -0.73
    ibus
    -0.72
    ulture
    -0.71
    mens
    -0.71
    ameron
    -0.70
    endon
    -0.70
    ierre
    -0.70
    annis
    -0.69
    arian
    -0.68
    POSITIVE LOGITS
     popup
    0.98
     automatically
    0.94
     ERROR
    0.86
     gib
    0.83
     readable
    0.83
    ministic
    0.79
     "%
    0.77
     cached
    0.77
    readable
    0.75
     formatted
    0.75
    Activations Density 0.314%

    No Known Activations