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. 2-RES-JB
    6. 2885
    Prev
    Next
    INDEX
    Explanations

    descriptions or actions related to personal involvement or experience

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "personally" in reference to individual experiences or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iens
    -0.77
     Grants
    -0.74
    Dispatch
    -0.72
     McKin
    -0.72
     Leap
    -0.71
     Maid
    -0.71
     Winds
    -0.70
     Weaver
    -0.70
     Gates
    -0.70
     Mechan
    -0.70
    POSITIVE LOGITS
     identifiable
    1.18
     personally
    0.95
     speaking
    0.83
     benefited
    0.83
    essage
    0.82
     exper
    0.82
     intervened
    0.79
     incrim
    0.79
    ographed
    0.79
     indul
    0.78
    Activations Density 0.005%

    No Known Activations