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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-RES-JB
    6. 19041
    Prev
    Next
    INDEX
    Explanations

    references to specific publications

    oai_token-act-pair · gpt-3.5-turbo

    references to academic works or publications

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

    No Comments

    Negative Logits
     responders
    -0.76
     unsafe
    -0.75
     standby
    -0.73
     shutdown
    -0.72
    Disable
    -0.71
    axy
    -0.71
     customers
    -0.70
    oppers
    -0.69
     Pokémon
    -0.68
     Poké
    -0.68
    POSITIVE LOGITS
     essays
    1.14
     ISBN
    1.12
     reprinted
    1.11
     unpublished
    1.02
     Literature
    0.98
     essay
    0.97
     manuscript
    0.97
     autobi
    0.96
    published
    0.96
     quotations
    0.95
    Activations Density 0.922%

    No Known Activations