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. 10-RES-JB
    6. 8967
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or places that are open or accessible to the general public

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illac
    -0.83
    icut
    -0.68
    NetMessage
    -0.67
    tackle
    -0.64
    sterdam
    -0.63
    dylib
    -0.63
    gy
    -0.63
    arella
    -0.62
    iHUD
    -0.61
    ibal
    -0.60
    POSITIVE LOGITS
     populace
    1.41
     masses
    1.39
     audience
    1.27
     public
    1.17
     community
    1.16
     wider
    1.14
     electorate
    1.14
     fanbase
    1.08
     rest
    1.07
     viewer
    1.06
    Activations Density 0.285%

    No Known Activations