© 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. 18724
    Prev
    Next
    INDEX
    Explanations

    government entities and official titles

    oai_token-act-pair · gpt-3.5-turbo

    references to government institutions and agencies

    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
    ;;;;
    -0.68
    Herm
    -0.67
    ¶æ
    -0.67
    ãĤ¨ãĥ«
    -0.67
    bryce
    -0.66
     [|
    -0.66
    EStream
    -0.66
    bearing
    -0.65
    é¾įå¥ij士
    -0.65
    thood
    -0.64
    POSITIVE LOGITS
     recognizes
    1.03
     considers
    1.03
     reacted
    1.02
     opted
    0.98
     has
    0.96
     acknowledges
    0.96
     announced
    0.95
     wants
    0.94
     insists
    0.94
     expects
    0.94
    Activations Density 0.355%

    No Known Activations