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. 4-RES-JB
    6. 18786
    Prev
    Next
    INDEX
    Explanations

    phrases related to numerical values and rankings

    oai_token-act-pair · gpt-3.5-turbo

    negative sentiments towards decisions or actions

    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
     Dickinson
    -0.89
     Scrib
    -0.89
     Burr
    -0.88
     Yelp
    -0.87
     Lovecraft
    -0.86
    ulhu
    -0.86
     Boone
    -0.83
     Vaughn
    -0.78
     Cobb
    -0.78
     Chandler
    -0.76
    POSITIVE LOGITS
    based
    1.11
    linked
    1.11
    backed
    1.10
    government
    1.05
    organ
    1.04
    bour
    1.03
    shaped
    1.03
    turned
    1.03
    Britain
    1.02
    national
    1.00
    Activations Density 0.270%

    No Known Activations