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. 4-RES-JB
    6. 22654
    Prev
    Next
    INDEX
    Explanations

    names or titles containing the word "Ban"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Ban" and its variations in context

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

    No Comments

    Negative Logits
    OTAL
    -0.73
     SERVICE
    -0.72
     IMAGES
    -0.70
    IRE
    -0.68
    paio
    -0.67
    æ©Ł
    -0.67
     gritty
    -0.63
     Democr
    -0.63
     Generations
    -0.63
     PROG
    -0.63
    POSITIVE LOGITS
    anas
    1.18
    quet
    1.13
    nered
    1.00
    jo
    0.99
    anan
    0.96
    arest
    0.92
    ner
    0.92
    ished
    0.89
    aji
    0.88
    ishment
    0.87
    Activations Density 0.013%

    No Known Activations