© 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. 3140
    Prev
    Next
    INDEX
    Explanations

    words related to various types of animals and an association between different concepts

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to specific brands or products, particularly in consumer contexts

    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
    ensable
    -0.63
    ±
    -0.58
    ¿½
    -0.54
    ente
    -0.53
    ãĤ¨
    -0.53
    -+-+
    -0.53
    otten
    -0.53
    inav
    -0.51
    ä
    -0.51
    most
    -0.51
    POSITIVE LOGITS
     largeDownload
    0.74
    lain
    0.65
    puff
    0.63
    DragonMagazine
    0.62
     sqor
    0.60
    hound
    0.56
    hedral
    0.56
     parchment
    0.56
    bleacher
    0.55
     IMAGES
    0.55
    Activations Density 0.952%

    No Known Activations