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. 17835
    Prev
    Next
    INDEX
    Explanations

    personal narratives or introspective thoughts

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to personal experiences and emotional reflections

    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
    actionDate
    -0.82
     subsequent
    -0.65
     streng
    -0.62
     Cosponsors
    -0.60
     subsequently
    -0.59
    during
    -0.58
    RESULTS
    -0.56
     continued
    -0.54
    armac
    -0.53
     afterward
    -0.53
    POSITIVE LOGITS
     imaginable
    0.74
     ain
    0.65
    ?,
    0.64
     proportions
    0.63
    !!!!
    0.63
    *,
    0.63
    !!
    0.63
    !,
    0.63
     stares
    0.63
     lol
    0.62
    Activations Density 0.558%

    No Known Activations