© 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. 8-RES-JB
    11. 6987
    Prev
    Next
    INDEX
    Explanations

    words related to mental states and cognitive processes

    oai_token-act-pair · gpt-3.5-turbo

    references to cognitive states and mental processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itures
    -0.94
    ModLoader
    -0.77
    ouk
    -0.77
     Estimated
    -0.74
     Policies
    -0.74
     Coverage
    -0.73
    ailable
    -0.72
    ospons
    -0.71
    ailability
    -0.71
    iatus
    -0.70
    POSITIVE LOGITS
     senses
    1.17
     faculties
    0.94
     numb
    0.93
     gland
    0.93
     neurons
    0.92
     glands
    0.88
     cortex
    0.87
     subconscious
    0.86
     nerves
    0.83
     craving
    0.81
    Activations Density 0.569%

    No Known Activations