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. 7-RES-JB
    6. 16659
    Prev
    Next
    INDEX
    Explanations

    past tense actions followed by a pronoun or noun

    oai_token-act-pair · gpt-3.5-turbo

    references to interpersonal dynamics and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     candidate
    -0.68
    £ı
    -0.67
     Founding
    -0.65
    isal
    -0.62
    alist
    -0.62
     Thou
    -0.61
     oneself
    -0.61
     candidates
    -0.59
     EC
    -0.59
     prospect
    -0.59
    POSITIVE LOGITS
     asleep
    0.81
     me
    0.80
     POV
    0.75
     alright
    0.71
    istar
    0.67
     okay
    0.65
    ses
    0.65
    bah
    0.64
     kindly
    0.64
    nt
    0.63
    Activations Density 0.604%

    No Known Activations