© 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. 4-RES-JB
    11. 23679
    Prev
    Next
    INDEX
    Explanations

    references to official documents or written communications

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "memo"

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

    No Comments

    Negative Logits
     Fen
    -0.70
    reek
    -0.69
    Georgia
    -0.63
    tool
    -0.61
     Greeks
    -0.59
    gpu
    -0.59
     Ethiop
    -0.59
     Kelvin
    -0.58
     Asians
    -0.58
     independents
    -0.57
    POSITIVE LOGITS
     memo
    1.08
    andum
    1.04
     memos
    0.91
    ufact
    0.85
    ographed
    0.82
    isode
    0.81
    ariat
    0.80
    osal
    0.80
    velop
    0.80
    izational
    0.79
    Activations Density 0.011%

    No Known Activations