© 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. 10251
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "Mind"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "Mind" or related discussions

    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
    DIR
    -0.82
    VEL
    -0.79
     Mehran
    -0.73
    aukee
    -0.72
    IDER
    -0.68
    reek
    -0.68
    OPLE
    -0.68
    è¦ļéĨĴ
    -0.68
     UEFA
    -0.68
    YING
    -0.67
    POSITIVE LOGITS
    fulness
    1.23
    Mind
    1.19
    mind
    1.18
    ful
    1.06
    bender
    0.96
     Mind
    0.95
    estinal
    0.85
    iac
    0.82
    storms
    0.82
    works
    0.81
    Activations Density 0.007%

    No Known Activations