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. 8-RES-JB
    6. 48
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to promoting or endorsing something

    oai_token-act-pair · gpt-3.5-turbo

    references to promoting various narratives or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fax
    -0.67
     Khe
    -0.66
    usercontent
    -0.64
     Paddock
    -0.63
     disg
    -0.62
     whence
    -0.60
    matched
    -0.59
    ney
    -0.59
    ÄŁ
    -0.59
     abruptly
    -0.57
    POSITIVE LOGITS
     virtues
    1.13
     superiority
    0.88
     ideals
    0.88
     awareness
    0.83
     lifestyles
    0.81
    independence
    0.80
    iveness
    0.79
     idea
    0.78
     individuality
    0.77
     notion
    0.77
    Activations Density 0.289%

    No Known Activations