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. 21216
    Prev
    Next
    INDEX
    Explanations

    segments indicating the original appearance and reproduction of articles

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the original source or authorship of an article

    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
    aura
    -0.74
    gui
    -0.73
    witch
    -0.70
    worms
    -0.69
    tra
    -0.68
    uka
    -0.67
    xus
    -0.67
    gas
    -0.67
    effect
    -0.66
    trap
    -0.65
    POSITIVE LOGITS
     Editorial
    0.92
     reprint
    0.92
     satire
    0.85
     Contribut
    0.80
    cerpt
    0.79
     reprinted
    0.76
     editorial
    0.75
     Published
    0.74
     reader
    0.74
     unpublished
    0.73
    Activations Density 0.491%

    No Known Activations