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. 6-RES-JB
    6. 11486
    Prev
    Next
    INDEX
    Explanations

    adjectives followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    past and present tense forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ESE
    -0.79
    glers
    -0.71
     congr
    -0.71
    osate
    -0.68
    Congratulations
    -0.67
    inav
    -0.67
     Brist
    -0.62
     Proceed
    -0.62
    ortmund
    -0.60
     Gw
    -0.60
    POSITIVE LOGITS
     certainly
    0.93
     definitely
    0.91
    nt
    0.87
     not
    0.87
     also
    0.86
     nonetheless
    0.81
     downright
    0.79
     NOT
    0.77
     hardly
    0.77
     plagued
    0.74
    Activations Density 0.519%

    No Known Activations