Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 6-RES-JB
    6. 18532
    Prev
    Next
    INDEX
    Explanations

    words related to ethnicities or nationalities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various types of physical forms and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONSORED
    -0.92
     Strait
    -0.77
    Bright
    -0.76
     Darling
    -0.76
    eele
    -0.75
     Subtle
    -0.73
    IZE
    -0.73
     Waters
    -0.72
    ATTLE
    -0.71
     Retirement
    -0.69
    POSITIVE LOGITS
    agra
    0.98
    abyte
    0.80
    olith
    0.78
    ule
    0.78
    atri
    0.77
    keyes
    0.75
    amp
    0.74
    Åį
    0.74
    ophobic
    0.74
    kered
    0.71
    Activations Density 0.178%

    No Known Activations