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. 18988
    Prev
    Next
    INDEX
    Explanations

    sentences talking about complexity and subjectivity

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to complexity and subjective processes

    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
    SPONSORED
    -0.83
    boro
    -0.76
    IELD
    -0.76
    Nice
    -0.72
    IDA
    -0.72
    owed
    -0.72
    psc
    -0.71
    vertising
    -0.70
    Virgin
    -0.70
    Via
    -0.69
    POSITIVE LOGITS
     complexities
    1.03
     depending
    1.02
     uneven
    1.01
     varies
    0.98
     fluct
    0.97
     messy
    0.97
     complicated
    0.94
     intric
    0.94
     unpredictable
    0.94
     uncertainties
    0.93
    Activations Density 0.727%

    No Known Activations