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

    Neuronpedia

    APICircuit 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. 17814
    Prev
    Next
    INDEX
    Explanations

    terms related to post-event activities, such as post-game interviews and comments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to games and competitive events, particularly in post-event 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
    Course
    -0.80
    ioxide
    -0.75
    vs
    -0.71
    urat
    -0.69
    osponsors
    -0.67
    anson
    -0.66
    Distance
    -0.65
    inus
    -0.64
    gado
    -0.62
    Container
    -0.62
    POSITIVE LOGITS
     checklist
    0.84
     festivities
    0.81
     adjustments
    0.77
     meal
    0.74
     briefing
    0.74
     analysis
    0.74
     greet
    0.74
     snack
    0.73
     arrivals
    0.72
     chatter
    0.72
    Activations Density 0.110%

    No Known Activations