© 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. 6820
    Prev
    Next
    INDEX
    Explanations

    phrases related to the longevity or existence of something

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being present or existing in a certain context

    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
    ãĤº
    -0.70
    ĸ
    -0.69
    eln
    -0.68
    oÄŁ
    -0.67
    enburg
    -0.67
    é¾į
    -0.67
    ascript
    -0.66
    uras
    -0.65
    idis
    -0.65
    ZE
    -0.64
    POSITIVE LOGITS
     corners
    0.87
     awhile
    0.73
    abouts
    0.72
     town
    0.70
     anymore
    0.69
     here
    0.67
     quieter
    0.65
     tremend
    0.64
     alot
    0.62
     Bland
    0.60
    Activations Density 0.029%

    No Known Activations