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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 9593
    Prev
    Next
    INDEX
    Explanations

    proper names

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotions or personal opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iaries
    -0.75
    PDF
    -0.75
     outset
    -0.73
    Attempts
    -0.73
    onding
    -0.72
    earchers
    -0.71
    igent
    -0.70
    utterstock
    -0.68
    istrates
    -0.68
     permitting
    -0.67
    POSITIVE LOGITS
    âĢ
    0.99
     Kanye
    0.98
     Elsa
    0.98
     âĢ
    0.96
    âĿ
    0.96
     he
    0.94
     Beyon
    0.90
     Blizz
    0.90
     Rih
    0.90
     Kyl
    0.89
    Activations Density 0.591%

    No Known Activations