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. 11-RES-JB
    6. 4698
    Prev
    Next
    INDEX
    Explanations

    phrases related to availability and prominence in a market or setting

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the availability and presence of products in the market

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ritical
    -0.62
    MpServer
    -0.60
     brunt
    -0.58
     Continued
    -0.58
     sarc
    -0.57
     Mach
    -0.56
     Chamber
    -0.54
    hner
    -0.54
     prolonged
    -0.53
    oultry
    -0.53
    POSITIVE LOGITS
     nowadays
    1.24
     today
    1.19
     lately
    0.99
    ãĤ¨ãĥ«
    0.85
    today
    0.83
     available
    0.83
     priced
    0.81
    available
    0.79
     commercially
    0.79
     cheaply
    0.76
    Activations Density 0.248%

    No Known Activations