© 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. 4-RES-JB
    11. 7487
    Prev
    Next
    INDEX
    Explanations

    references to the concept of consciousness

    oai_token-act-pair · gpt-3.5-turbo

    references to consciousness and its various states or aspects

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

    No Comments

    Negative Logits
    coni
    -0.78
    ãĥ³ãĤ¸
    -0.67
    ctions
    -0.65
    å¸
    -0.64
    jon
    -0.62
     rough
    -0.61
     PM
    -0.60
     Maurit
    -0.59
     unpublished
    -0.58
    headers
    -0.57
    POSITIVE LOGITS
    ysis
    0.98
     consciousness
    0.89
    edly
    0.89
    es
    0.87
    ively
    0.83
    lessness
    0.82
    ibility
    0.82
     Conscious
    0.81
    mble
    0.79
    akens
    0.78
    Activations Density 0.013%

    No Known Activations