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. 4-RES-JB
    6. 23147
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to named entities, particularly those related to a specific monetary award or plan named 'B'

    oai_token-act-pair · gpt-3.5-turbo

    references to the letter 'B' in various contexts, especially in relation to budgets and individuals

    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
     Gutenberg
    -0.86
     por
    -0.62
     Pharaoh
    -0.61
     choir
    -0.60
     Cheong
    -0.60
     dere
    -0.60
     Voldemort
    -0.59
    wcsstore
    -0.58
     Panama
    -0.58
     Lerner
    -0.57
    POSITIVE LOGITS
    urt
    1.09
    rug
    1.09
    razen
    1.08
    aked
    1.05
    rows
    1.04
    odies
    1.04
    amboo
    1.02
    rief
    1.02
    asket
    1.01
    raid
    1.01
    Activations Density 0.057%

    No Known Activations