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. 23419
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations in a technical or governmental context

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms related to organizations or governing bodies

    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
    ãĤ¦ãĤ¹
    -0.90
    ãĤ¹ãĥĪ
    -0.87
    ãĤ°
    -0.86
    Magikarp
    -0.84
    ãĤª
    -0.83
    \":
    -0.82
    ãĥīãĥ©ãĤ´ãĥ³
    -0.82
    )=(
    -0.81
    ãĤ¶
    -0.81
    ãĤ¤ãĥĪ
    -0.77
    POSITIVE LOGITS
    FI
    1.06
    TF
    0.98
    FP
    0.95
    SA
    0.93
    ouble
    0.93
    FG
    0.90
    SS
    0.89
    RS
    0.88
    WD
    0.88
    DP
    0.87
    Activations Density 0.154%

    No Known Activations