© 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. 1-RES-JB
    11. 9528
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Marsh" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to "Marshmallow" and other related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deaf
    -0.76
    anooga
    -0.67
     tense
    -0.65
     reper
    -0.65
     traged
    -0.64
    lihood
    -0.64
    abama
    -0.62
     dism
    -0.62
     fugitive
    -0.61
     circumst
    -0.61
    POSITIVE LOGITS
    mallow
    1.68
     Marsh
    1.20
    adow
    0.95
    Marsh
    0.89
    alling
    0.87
    alls
    0.86
    als
    0.84
    olini
    0.84
    bryce
    0.79
    wolves
    0.78
    Activations Density 0.005%

    No Known Activations