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. 19991
    Prev
    Next
    INDEX
    Explanations

    phrases related to marketing and product promotion

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation marks and closely related sentence structures

    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
     quir
    -0.86
     uncom
    -0.72
     wed
    -0.70
     hob
    -0.69
     aides
    -0.68
     pals
    -0.66
     impulse
    -0.65
     tangled
    -0.65
     sharply
    -0.65
     fatally
    -0.64
    POSITIVE LOGITS
     Lastly
    1.44
     Additionally
    1.41
     Whilst
    1.37
     Therefore
    1.37
     Furthermore
    1.33
     However
    1.32
     Needless
    1.29
     Lets
    1.26
     Unfortunately
    1.21
    Therefore
    1.19
    Activations Density 0.685%

    No Known Activations