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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 23106
    Prev
    Next
    INDEX
    Explanations

    concepts related to deep thinking or contemplation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "thought" and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ARDS
    -0.70
    ALL
    -0.66
    BIP
    -0.66
    lehem
    -0.64
     Peninsula
    -0.64
    Availability
    -0.63
    ards
    -0.63
    anca
    -0.61
     toe
    -0.60
     Tens
    -0.58
    POSITIVE LOGITS
    fulness
    1.26
    fully
    1.20
     provoking
    1.15
    lessly
    1.15
    lessness
    0.95
    less
    0.85
    orial
    0.82
    borgh
    0.81
    sworth
    0.81
    ful
    0.79
    Activations Density 0.032%

    No Known Activations