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. 18277
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or place names

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the sequence "agh"

    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
     indo
    -0.77
     Hoover
    -0.74
     Olympia
    -0.72
    ļéĨĴ
    -0.70
     Hercules
    -0.68
    PDATE
    -0.65
     Curiosity
    -0.64
     Glock
    -0.63
    ership
    -0.63
     basketball
    -0.62
    POSITIVE LOGITS
    avan
    1.17
    agh
    1.17
    ttp
    1.15
    allery
    1.08
    awa
    1.03
    ilipp
    1.03
    orst
    0.96
    ertility
    0.95
    APTER
    0.93
    patrick
    0.92
    Activations Density 0.004%

    No Known Activations