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. 9-RES-JB
    6. 7877
    Prev
    Next
    INDEX
    Explanations

    mentions of and concerns related to racial or ethnic issues, particularly focusing on communities of color

    oai_token-act-pair · gpt-3.5-turbo

    references to communities of color and their experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pload
    -0.82
    pex
    -0.80
    Spl
    -0.79
    Thunder
    -0.78
    Lock
    -0.76
     Heist
    -0.75
    aghetti
    -0.75
    Shock
    -0.74
    suit
    -0.74
    ibal
    -0.74
    POSITIVE LOGITS
     incarcerated
    1.00
     residing
    0.99
     backgrounds
    0.96
     living
    0.96
     populations
    0.93
     communities
    0.92
     disadvantaged
    0.90
     disproportionately
    0.89
     who
    0.89
     minorities
    0.88
    Activations Density 0.190%

    No Known Activations