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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-RES-JB
    6. 17449
    Prev
    Next
    INDEX
    Explanations

    words related to thinking deeply or considering different aspects of a situation

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "mull" and other terms related to contemplation and deep thinking

    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
    inters
    -0.64
    alle
    -0.62
    lez
    -0.58
    CVE
    -0.57
    ĪĴ
    -0.57
    arge
    -0.56
    ifacts
    -0.56
    dimension
    -0.55
    anch
    -0.55
     coordinator
    -0.54
    POSITIVE LOGITS
     contemplating
    0.94
     "$:/
    0.93
     mull
    0.92
     contemplate
    0.91
    iors
    0.86
    atorium
    0.83
    spection
    0.81
    pai
    0.80
     aloud
    0.79
    swer
    0.74
    Activations Density 0.021%

    No Known Activations