© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 10596
    Prev
    Next
    INDEX
    Explanations

    mentions of the term 'marsh' with varying degrees of association

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "marsh" and its related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deaf
    -0.76
     vest
    -0.73
    lihood
    -0.66
     Jinn
    -0.65
     trickle
    -0.65
     Belt
    -0.65
    hedral
    -0.62
    zzle
    -0.62
     dread
    -0.61
     thumbs
    -0.60
    POSITIVE LOGITS
    mallow
    1.93
    alling
    1.53
    alls
    1.44
    aling
    1.36
    als
    1.30
    alled
    1.27
    aled
    1.22
    alties
    1.06
    all
    1.01
    adow
    1.00
    Activations Density 0.030%

    No Known Activations