© 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. 0-RES-JB
    6. 7680
    Prev
    Next
    INDEX
    Explanations

    words related to thoughts or mental processes/actions

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'mind' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iers
    -0.68
    ér
    -0.65
    isf
    -0.65
    jun
    -0.63
    iability
    -0.62
     Saf
    -0.62
     Bian
    -0.62
    gat
    -0.61
    prot
    -0.60
    eah
    -0.60
    POSITIVE LOGITS
     mind
    3.86
     minds
    2.76
    mind
    2.63
     Mind
    2.35
    Mind
    2.06
     psyche
    1.61
     imagination
    1.61
     mindset
    1.50
     brain
    1.45
     minded
    1.32
    Activations Density 0.017%

    No Known Activations