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. 11-RES-JB
    6. 22927
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking on roles or responsibilities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to taking on roles, responsibilities, and assumptions in various contexts

    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
    ivers
    -0.73
    apers
    -0.67
    through
    -0.67
    Reviewed
    -0.66
    Links
    -0.66
    Alert
    -0.65
    edia
    -0.65
    ope
    -0.64
    ratulations
    -0.64
    rehensive
    -0.63
    POSITIVE LOGITS
     mantle
    1.71
     role
    1.66
     responsibilities
    1.51
     duties
    1.45
     responsibility
    1.41
     task
    1.41
     roles
    1.35
     reins
    1.35
     helm
    1.27
     throne
    1.19
    Activations Density 0.276%

    No Known Activations