© 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. 2-RES-JB
    11. 9109
    Prev
    Next
    INDEX
    Explanations

    adverbs and adjectives related to consciousness and unconsciousness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to subconscious and conscious awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    annis
    -0.73
    andals
    -0.72
     Jericho
    -0.68
    adr
    -0.68
    IDER
    -0.68
    EGA
    -0.65
    addafi
    -0.65
     LIC
    -0.63
    URR
    -0.63
     Argent
    -0.63
    POSITIVE LOGITS
     subconscious
    1.19
     unconsciously
    0.92
    mind
    0.84
     mind
    0.83
    conscious
    0.79
    ministic
    0.75
     disson
    0.74
    brain
    0.72
     impulse
    0.72
    ritten
    0.72
    Activations Density 0.010%

    No Known Activations