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. 10-RES-JB
    6. 2547
    Prev
    Next
    INDEX
    Explanations

    sentences related to software development, company plans, and product launches

    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
    ocaust
    -0.84
     negro
    -0.83
     wretched
    -0.81
     dreaded
    -0.80
     Deaths
    -0.80
     depl
    -0.77
     disgrace
    -0.77
    ghazi
    -0.76
     ruin
    -0.74
     sorrow
    -0.72
    POSITIVE LOGITS
     partnerships
    1.36
     interoper
    1.28
     rollout
    1.23
     SDK
    1.20
     partnering
    1.19
     apps
    1.15
     partnered
    1.13
     IoT
    1.13
     integrate
    1.12
     integration
    1.12
    Activations Density 0.797%

    No Known Activations