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. 11-RES-JB
    6. 20328
    Prev
    Next
    INDEX
    Explanations

    superlatives and rankings

    oai_token-act-pair · gpt-3.5-turbo

    references to notable people or entities in a superlative context

    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
    Results
    -0.71
    wards
    -0.70
    uitous
    -0.68
    isson
    -0.65
    ward
    -0.64
    resso
    -0.63
    ï¸
    -0.62
    orrow
    -0.60
    yden
    -0.60
    RESULTS
    -0.60
    POSITIVE LOGITS
     world
    1.44
     history
    1.31
     entire
    1.26
     country
    1.21
     universe
    1.19
     nation
    1.12
     galaxy
    1.04
     WORLD
    1.04
     whole
    1.03
     Universe
    1.03
    Activations Density 0.104%

    No Known Activations