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. 17185
    Prev
    Next
    INDEX
    Explanations

    terms related to gentrification

    oai_token-act-pair · gpt-3.5-turbo

    references to gentrification and related terms

    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
    lihood
    -0.77
    hari
    -0.73
    ibaba
    -0.73
    zsche
    -0.68
    gered
    -0.68
    nergy
    -0.68
    phrine
    -0.67
     Bones
    -0.65
    sha
    -0.65
    umar
    -0.65
    POSITIVE LOGITS
    ubb
    0.84
     Hots
    0.81
    lest
    0.76
    ardless
    0.75
    iour
    0.75
     gent
    0.73
    ards
    0.71
    ified
    0.70
    sylv
    0.70
    iants
    0.69
    Activations Density 0.025%

    No Known Activations