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. 8-RES-JB
    6. 5759
    Prev
    Next
    INDEX
    Explanations

    technical keywords and programming terms

    oai_token-act-pair · gpt-3.5-turbo

    specific keywords and technology-related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0000000000000000
    -0.79
    AIDS
    -0.77
    ãģĨ
    -0.72
    ||||
    -0.71
    assis
    -0.69
    acio
    -0.69
     ..........
    -0.68
    avering
    -0.67
    orate
    -0.67
    Bey
    -0.66
    POSITIVE LOGITS
     recommends
    1.11
     relies
    1.01
     uses
    1.01
     prefers
    1.00
     tends
    0.97
     utilizes
    0.97
     designers
    0.96
     defines
    0.96
     distinguishes
    0.94
     lacks
    0.93
    Activations Density 0.671%

    No Known Activations