© 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. 10-RES-JB
    11. 16058
    Prev
    Next
    INDEX
    Explanations

    references to the concept of the mind

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'mind' and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vide
    -0.70
     Mehran
    -0.69
    TAIN
    -0.68
     Aval
    -0.67
    Recomm
    -0.66
     Legend
    -0.65
    ICAN
    -0.63
    Reviewed
    -0.62
     Carly
    -0.62
    aukee
    -0.58
    POSITIVE LOGITS
    fulness
    1.20
    lessly
    1.14
    storms
    1.12
    share
    1.09
    bender
    1.07
    fuck
    1.06
    scape
    1.05
    ful
    0.99
    blow
    0.99
    fully
    0.98
    Activations Density 0.034%

    No Known Activations