© 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. 6039
    Prev
    Next
    INDEX
    Explanations

    phrases related to changes or endings

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to analysis and evaluation of circumstances

    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
    «ĺ
    -0.59
    cially
    -0.58
     widely
    -0.57
    urther
    -0.55
     mutually
    -0.54
    İĭ
    -0.54
    ationally
    -0.54
    appropriately
    -0.54
     urgently
    -0.54
    isively
    -0.54
    POSITIVE LOGITS
     nowadays
    0.99
     lately
    0.94
     haha
    0.71
     compared
    0.68
     (~
    0.64
     vibe
    0.63
     stuff
    0.62
     dudes
    0.62
     tho
    0.61
     affair
    0.61
    Activations Density 0.801%

    No Known Activations