© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 6896
    Prev
    Next
    INDEX
    Explanations

    verbs related to mental processes, primarily focusing on the act of thinking

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iona
    -0.61
     Peninsula
    -0.59
     Peaks
    -0.58
    çĦ
    -0.57
    feeding
    -0.55
     Temper
    -0.53
    Availability
    -0.53
     Channel
    -0.53
    ulia
    -0.53
    translation
    -0.52
    POSITIVE LOGITS
     aloud
    1.05
     ABOUT
    1.02
     about
    1.01
    about
    0.84
     strategically
    0.81
     creatively
    0.81
     twice
    0.79
    dress
    0.77
    estyle
    0.76
     differently
    0.75
    Activations Density 0.071%

    No Known Activations