© 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. 9-RES-JB
    11. 1753
    Prev
    Next
    INDEX
    Explanations

    numbers of people or quantities mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to large groups of people or populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.87
    ¿½
    -0.80
    ķ
    -0.77
    ãĤ¦ãĤ¹
    -0.76
    ĵ
    -0.74
    prem
    -0.69
    escription
    -0.68
    £
    -0.67
    ©¶æ
    -0.65
    ¡
    -0.64
    POSITIVE LOGITS
     perished
    1.14
     whom
    1.08
     who
    1.04
     alive
    0.98
     died
    0.93
     murdered
    0.90
     volunteered
    0.90
     unlucky
    0.88
     ;)
    0.88
     sacrificed
    0.88
    Activations Density 0.585%

    No Known Activations