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. 20687
    Prev
    Next
    INDEX
    Explanations

    terms related to actions or initiatives happening on a nationwide scale

    oai_token-act-pair · gpt-3.5-turbo

    terms related to online accessibility and collaboration

    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
    Americans
    -0.94
    lees
    -0.94
    stories
    -0.94
    Frames
    -0.93
    bits
    -0.91
    osaurs
    -0.90
    Tags
    -0.89
    tics
    -0.89
    ernels
    -0.88
    Nazis
    -0.88
    POSITIVE LOGITS
     version
    1.11
     advisory
    0.99
     solution
    0.98
     evaluation
    0.97
     arrangement
    0.96
     suite
    0.96
     regimen
    0.95
     panel
    0.95
     edition
    0.95
     batch
    0.94
    Activations Density 0.386%

    No Known Activations