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. 21862
    Prev
    Next
    INDEX
    Explanations

    references to URLs in text

    oai_token-act-pair · gpt-3.5-turbo

    punctuation or specific formatting used in URLs and links

    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
    PDATE
    -0.85
    anooga
    -0.81
     conclud
    -0.77
    ¯¯
    -0.76
    -+-+
    -0.76
     srfAttach
    -0.75
     grounding
    -0.74
    Orderable
    -0.72
    ÃĥÃĤÃĥÃĤ
    -0.68
     rall
    -0.67
    POSITIVE LOGITS
    github
    1.27
    google
    1.25
    dat
    1.18
    cdn
    1.14
    debian
    1.09
    blogspot
    1.08
    assetsadobe
    1.07
    bleacher
    1.03
    amazon
    1.01
    adobe
    1.01
    Activations Density 0.035%

    No Known Activations