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. 0-RES-JB
    6. 19469
    Prev
    Next
    INDEX
    Explanations

    references to the term "Ag" and potentially related entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Ag" and its associated contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    netflix
    -0.73
     peripheral
    -0.72
    ighth
    -0.69
     coloring
    -0.67
    OPLE
    -0.67
    blance
    -0.67
    olson
    -0.65
    ixtape
    -0.65
     recreate
    -0.64
    istry
    -0.63
    POSITIVE LOGITS
     Ag
    3.74
    Ag
    2.65
     ag
    1.68
     AG
    1.63
    ag
    1.18
     agile
    1.13
    AG
    1.11
     Agg
    1.10
     Ap
    1.10
     Agric
    1.07
    Activations Density 0.010%

    No Known Activations