Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 21091
    Prev
    Next
    INDEX
    Explanations

    instances of the word "unconscious" and related concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to states of unconsciousness

    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
    mm
    -0.68
    pher
    -0.67
     premier
    -0.67
    lv
    -0.66
    mite
    -0.65
     Contra
    -0.65
    ium
    -0.64
     sold
    -0.63
    ÙIJ
    -0.62
     haw
    -0.62
    POSITIVE LOGITS
     unconscious
    4.20
     subconscious
    2.37
     unconsciously
    1.79
     conscious
    1.63
    conscious
    1.58
     consciousness
    1.43
     incapac
    1.36
     asleep
    1.34
     lifeless
    1.19
     psyche
    1.19
    Activations Density 0.025%

    No Known Activations