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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 1989
    Prev
    Next
    INDEX
    Explanations

    phrases indicating someone or something being specifically highlighted or targeted

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "singled out."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    veyard
    -0.73
    ipeg
    -0.71
    istor
    -0.71
     upkeep
    -0.66
    issance
    -0.65
    anos
    -0.64
     embr
    -0.63
    emi
    -0.63
    anwhile
    -0.62
     liaison
    -0.61
    POSITIVE LOGITS
     è£ıè
    0.85
     exceptions
    0.77
    Reason
    0.72
    posts
    0.67
    IFIED
    0.65
     criteria
    0.65
    STDOUT
    0.65
    ãĤī
    0.64
     Exception
    0.64
    Section
    0.64
    Activations Density 0.035%

    No Known Activations