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. 1-RES-JB
    6. 14862
    Prev
    Next
    INDEX
    Explanations

    acronyms related to various fields, such as "PE" for physical education or "IA" for internal affairs

    oai_token-act-pair · gpt-3.5-turbo

    references to private equity (PE) and its impact on various industries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ£
    -0.82
    night
    -0.82
    ãĤ·ãĥ£
    -0.77
    ãĥĦ
    -0.74
    ãĤ±
    -0.72
    flies
    -0.72
    ãĤ¼ãĤ¦ãĤ¹
    -0.71
    frames
    -0.71
    ãĥģ
    -0.70
    ãĥ´ãĤ¡
    -0.70
    POSITIVE LOGITS
    PE
    1.30
    OPLE
    1.12
    OTUS
    0.97
    zzo
    0.94
    ACE
    0.86
     PE
    0.84
    zza
    0.79
    minent
    0.79
    etition
    0.77
    ggie
    0.77
    Activations Density 0.005%

    No Known Activations