© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 16323
    Prev
    Next
    INDEX
    Explanations

    mentions of specific businesses or product names, likely related to marketing or branding

    oai_token-act-pair · gpt-3.5-turbo

    references to specific people or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eleph
    -0.98
     conclud
    -0.96
    anwhile
    -0.94
    theless
    -0.92
     pione
    -0.91
     ende
    -0.87
     enthusi
    -0.87
    é¾įå¥ij士
    -0.86
    Þ
    -0.82
     referen
    -0.82
    POSITIVE LOGITS
    inar
    0.98
    astery
    0.91
    immer
    0.88
    ombat
    0.87
    itars
    0.83
    istries
    0.83
    etry
    0.78
    inct
    0.78
    stice
    0.78
    iffe
    0.78
    Activations Density 0.131%

    No Known Activations