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. 11-RES-JB
    6. 2959
    Prev
    Next
    INDEX
    Explanations

    the word "experience" or any variations of it

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the root word "experience" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Osw
    -0.63
     KR
    -0.63
     flat
    -0.62
     flats
    -0.61
     contiguous
    -0.61
     wedge
    -0.60
    flat
    -0.58
     goodbye
    -0.58
     aloud
    -0.58
     Strauss
    -0.57
    POSITIVE LOGITS
    ienced
    2.01
    iences
    1.88
    ience
    1.79
    imental
    1.70
    iments
    1.66
    iment
    1.60
    ient
    1.52
    ien
    1.41
    iency
    1.26
    iance
    1.21
    Activations Density 0.040%

    No Known Activations