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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 6185
    Prev
    Next
    INDEX
    Explanations

    titles or descriptions of academic articles or books

    oai_token-act-pair · gpt-3.5-turbo

    periods and formatting related to academic or scientific references

    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
     rall
    -0.85
    onga
    -0.83
     glim
    -0.81
     entreprene
    -0.80
     tremend
    -0.79
     mosqu
    -0.79
     way
    -0.77
     quir
    -0.77
     snowball
    -0.76
     crab
    -0.75
    POSITIVE LOGITS
     Retrieved
    1.33
     Includes
    1.26
    txt
    1.19
    htm
    1.16
     Also
    1.12
    jpg
    1.10
     Accessed
    1.09
    html
    1.09
     However
    1.06
    aspx
    1.06
    Activations Density 0.597%

    No Known Activations