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. 2809
    Prev
    Next
    INDEX
    Explanations

    explanations or tutorials in the context of software development

    oai_token-act-pair · gpt-3.5-turbo

    tutorial-related content focusing on explanations or instructions

    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
    usercontent
    -0.71
    ween
    -0.68
    uries
    -0.68
    pressed
    -0.64
    adjusted
    -0.63
    olls
    -0.63
    estate
    -0.63
     extinguished
    -0.62
     condol
    -0.62
    blood
    -0.62
    POSITIVE LOGITS
     instructional
    1.03
     Instruct
    0.98
     topics
    0.91
     tutorials
    0.91
    utorial
    0.85
     tutorial
    0.84
     guides
    0.83
     beginners
    0.82
    Instruct
    0.80
     learners
    0.78
    Activations Density 0.367%

    No Known Activations