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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-RES-JB
    6. 5134
    Prev
    Next
    INDEX
    Explanations

    phrases related to data or technical details

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     forwarding
    -0.68
    ierre
    -0.66
    iating
    -0.64
     lamb
    -0.64
    aroo
    -0.64
     bombshell
    -0.63
     sooner
    -0.62
    onga
    -0.62
    mitt
    -0.60
     stranger
    -0.60
    POSITIVE LOGITS
     Includes
    1.23
     Originally
    1.11
     Contains
    1.06
     Allows
    1.06
     Uses
    1.04
     Also
    1.03
     Usually
    1.00
     Provides
    0.99
     These
    0.97
     Each
    0.97
    Activations Density 0.299%

    No Known Activations