© 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. 11-RES-JB
    11. 17113
    Prev
    Next
    INDEX
    Explanations

    descriptions of large financial amounts and construction projects

    oai_token-act-pair · gpt-3.5-turbo

    references to infrastructure projects and related financial details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whilst
    -1.02
     Whilst
    -0.94
     organise
    -0.81
    izoph
    -0.79
    Firstly
    -0.77
    xual
    -0.77
     emphas
    -0.77
     Firstly
    -0.73
     secondly
    -0.72
     recognise
    -0.71
    POSITIVE LOGITS
     Amtrak
    1.31
     Interstate
    1.17
     federal
    1.16
     Nevada
    1.15
     Albuquerque
    1.14
     FAA
    1.14
     Chattanooga
    1.13
     Delaware
    1.11
     Alaska
    1.09
     Navajo
    1.09
    Activations Density 0.810%

    No Known Activations