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. 23396
    Prev
    Next
    INDEX
    Explanations

    names or terms related to groups or organizations with the word "Gang"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific groups or collectives, particularly in a context related to cultural or criminal organizations

    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
    ITE
    -0.83
    phia
    -0.81
    IGHT
    -0.76
    etheless
    -0.71
    ight
    -0.71
    ention
    -0.71
    landish
    -0.68
    =]
    -0.68
    nesday
    -0.68
    ights
    -0.67
    POSITIVE LOGITS
    lasses
    1.10
    aroo
    1.04
    heng
    0.89
     Kang
    0.88
    pak
    0.88
    ulative
    0.87
    nam
    0.85
     Gang
    0.84
    mong
    0.83
    iov
    0.81
    Activations Density 0.012%

    No Known Activations