© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    6. 7032
    Prev
    Next
    INDEX
    Explanations

    phrases related to cognitive processes and deep thinking

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "thought" or "thinking."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Peninsula
    -0.68
    opard
    -0.65
     Tens
    -0.63
     toe
    -0.62
    BIP
    -0.62
    Availability
    -0.61
    ALL
    -0.60
     Mehran
    -0.60
     pige
    -0.59
     Hi
    -0.59
    POSITIVE LOGITS
    fulness
    1.34
     provoking
    1.31
    fully
    1.14
    lessly
    1.13
    crime
    1.10
    lessness
    0.99
     processes
    0.96
     experiment
    0.92
    less
    0.89
     process
    0.89
    Activations Density 0.055%

    No Known Activations