© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 7760
    Prev
    Next
    INDEX
    Explanations

    elements related to specific professions or tasks

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns and keywords related to diverse subjects such as animals, emotions, objects, and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Adren
    -0.63
     Naz
    -0.60
    eki
    -0.58
    bris
    -0.57
    idth
    -0.56
    ometimes
    -0.55
    ymm
    -0.54
     Pic
    -0.54
    ente
    -0.53
     Brilliant
    -0.53
    POSITIVE LOGITS
     itself
    0.73
     oneself
    0.70
     himself
    0.69
     motif
    0.68
     herself
    0.66
     myself
    0.65
    ).[
    0.65
     peripher
    0.63
     alone
    0.62
     Himself
    0.62
    Activations Density 0.873%

    No Known Activations