© 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. 1-RES-JB
    11. 24290
    Prev
    Next
    INDEX
    Explanations

    verbs related to being in a difficult or helpless situation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stranded"

    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
    aic
    -0.87
    apa
    -0.78
    obby
    -0.77
    ificantly
    -0.77
    insula
    -0.74
    orney
    -0.74
    leans
    -0.73
    eon
    -0.72
    sych
    -0.70
    venants
    -0.69
    POSITIVE LOGITS
     stranded
    1.60
     Kraken
    0.74
     Luffy
    0.73
     trapped
    0.71
    ãĥĺ
    0.69
    ãĤ´
    0.69
    ãĤ§
    0.69
     Icelandic
    0.68
     plag
    0.68
     Vector
    0.66
    Activations Density 0.006%

    No Known Activations