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. 8-RES-JB
    6. 18228
    Prev
    Next
    INDEX
    Explanations

    terms related to the Silicon Valley

    oai_token-act-pair · gpt-3.5-turbo

    references to Silicon Valley and its associated elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¤ãĥĪ
    -0.84
    onom
    -0.75
    urnal
    -0.71
    weather
    -0.71
    eworld
    -0.70
    atur
    -0.68
    hower
    -0.68
    ollow
    -0.67
    odox
    -0.67
    otte
    -0.67
    POSITIVE LOGITS
     equivalents
    0.71
    ioxide
    0.67
     (%
    0.64
     cutoff
    0.59
     fri
    0.57
    ®,
    0.57
    âĦ¢:
    0.57
     synth
    0.57
     (~
    0.57
     3000
    0.56
    Activations Density 0.396%

    No Known Activations