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. 4-RES-JB
    6. 5503
    Prev
    Next
    INDEX
    Explanations

    expressions involving loyalty or support

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "stand by" in various contexts

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

    No Comments

    Negative Logits
    Runner
    -0.71
    asy
    -0.66
    ginx
    -0.65
    SPONSORED
    -0.64
    Reilly
    -0.61
    aminer
    -0.60
    ETF
    -0.60
    allo
    -0.60
    >[
    -0.60
     pains
    -0.60
    POSITIVE LOGITS
     virtue
    1.18
    products
    1.04
    laws
    1.02
    product
    0.91
     fiat
    0.86
    akuya
    0.84
     leaps
    0.80
    catch
    0.78
     proxy
    0.76
    gone
    0.74
    Activations Density 0.180%

    No Known Activations