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. 15198
    Prev
    Next
    INDEX
    Explanations

    statements indicating relief or resolution

    oai_token-act-pair · gpt-3.5-turbo

    references to decision-making and options

    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
    âĢ
    -1.26
     âĢ
    -1.16
    [/
    -1.16
    âĹ
    -1.05
    ´
    -1.03
    ãĢ
    -1.02
    ————————————————
    -1.01
     Whilst
    -0.99
    îĢ
    -0.97
    à¼
    -0.95
    POSITIVE LOGITS
     Buddy
    0.94
     Sonny
    0.92
     Rudolph
    0.90
     Elvis
    0.89
     Philly
    0.89
     dudes
    0.87
     Johnny
    0.87
     Rudy
    0.84
     Willie
    0.83
     Doodle
    0.83
    Activations Density 0.976%

    No Known Activations