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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 5464
    Prev
    Next
    INDEX
    Explanations

    tech-related terms and functions involving programming languages

    oai_token-act-pair · gpt-3.5-turbo

    symbols and special characters used in coding or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ittal
    -0.95
     thor
    -0.79
    ischer
    -0.78
    anging
    -0.73
    >[
    -0.72
     babys
    -0.72
     outl
    -0.69
    isch
    -0.69
    andre
    -0.68
    oubted
    -0.67
    POSITIVE LOGITS
     Enhancement
    1.02
    Premium
    0.92
     Month
    0.87
     Enhance
    0.87
     Increases
    0.86
     Modes
    0.85
     Ratio
    0.85
     Ages
    0.84
     Groups
    0.82
     Types
    0.82
    Activations Density 0.644%

    No Known Activations