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. 6-RES-JB
    6. 22997
    Prev
    Next
    INDEX
    Explanations

    phrases related to knowing or learning about something

    oai_token-act-pair · gpt-3.5-turbo

    instances where reports or awareness of important information or events are mentioned

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soever
    -0.74
    icates
    -0.72
    ãĥ¯
    -0.68
    uckles
    -0.67
     Pwr
    -0.67
    reau
    -0.65
     Brenda
    -0.65
    obar
    -0.64
    orate
    -0.64
    ulo
    -0.64
    POSITIVE LOGITS
     impending
    1.13
     dangers
    0.88
     existence
    0.87
     possibility
    0.83
     potential
    0.78
     phenomenon
    0.78
     nuances
    0.78
     situation
    0.77
     imminent
    0.77
     occurrence
    0.76
    Activations Density 0.320%

    No Known Activations