Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 8240
    Prev
    Next
    INDEX
    Explanations

    adverbs that intensify an accompanying adjective or verb

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "incredibly" and its variations used to express strong feelings or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icip
    -0.75
    icipated
    -0.73
    Runner
    -0.71
    eto
    -0.69
     Continued
    -0.67
    igi
    -0.66
    oral
    -0.65
    osate
    -0.65
    edom
    -0.64
    igate
    -0.63
    POSITIVE LOGITS
     expensive
    0.77
     uncomfortable
    0.76
     important
    0.75
     difficult
    0.75
     fascinating
    0.73
     complicated
    0.72
     intricate
    0.72
     valuable
    0.72
    beit
    0.72
     inefficient
    0.71
    Activations Density 0.026%

    No Known Activations