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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-RES-JB
    6. 11936
    Prev
    Next
    INDEX
    Explanations

    phrases related to goals or intentions

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases that suggest cumulative actions or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rored
    -0.65
    kson
    -0.64
    riad
    -0.60
    awed
    -0.58
    Lens
    -0.58
    thought
    -0.58
    EMS
    -0.56
    icol
    -0.56
    Morning
    -0.55
    cloth
    -0.54
    POSITIVE LOGITS
     to
    1.23
     minimize
    1.15
     establish
    1.12
     promote
    1.12
     ensure
    1.12
    to
    1.12
     preserve
    1.11
     educate
    1.10
     maximize
    1.10
     satisfy
    1.10
    Activations Density 0.390%

    No Known Activations