© 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. 2-RES-JB
    11. 8368
    Prev
    Next
    INDEX
    Explanations

    names related to a particular person, possibly a politician

    oai_token-act-pair · gpt-3.5-turbo

    words related to reductions or decreases in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    printf
    -0.71
    Ü
    -0.67
    sung
    -0.66
    lived
    -0.66
    DOC
    -0.61
     nep
    -0.59
    SUP
    -0.59
    mbuds
    -0.58
     ãĤµ
    -0.57
    live
    -0.57
    POSITIVE LOGITS
    uce
    1.39
    uces
    1.11
    llor
    1.01
    uction
    0.98
    uced
    0.95
    xual
    0.94
    eer
    0.90
    lect
    0.87
    lectic
    0.85
    ucing
    0.82
    Activations Density 0.012%

    No Known Activations