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. 6741
    Prev
    Next
    INDEX
    Explanations

    sentences containing personal comments or reflections

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal sentiments or reflections on societal issues

    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
    secret
    -0.66
    \-
    -0.64
    amon
    -0.61
     speculation
    -0.60
    sbm
    -0.59
    indal
    -0.58
     unknown
    -0.57
     disastrous
    -0.56
    unknown
    -0.56
     devastating
    -0.55
    POSITIVE LOGITS
     sanity
    1.11
     decency
    1.08
     sane
    1.04
    respect
    1.04
     calmed
    0.98
     honesty
    0.93
     unbiased
    0.93
    cknow
    0.93
     honest
    0.92
     sensible
    0.90
    Activations Density 1.540%

    No Known Activations