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. 14540
    Prev
    Next
    INDEX
    Explanations

    specific dates in various formats

    oai_token-act-pair · gpt-3.5-turbo

    specific years or dates mentioned in the text

    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
    amins
    -0.67
     plur
    -0.66
     endless
    -0.65
    onite
    -0.62
     Wonders
    -0.61
    ousel
    -0.59
    advertisement
    -0.59
    outer
    -0.58
    und
    -0.57
     noisy
    -0.56
    POSITIVE LOGITS
    displayText
    0.69
     Referred
    0.67
    mr
    0.67
    isSpecialOrderable
    0.67
     UTC
    0.66
    âĸĪ
    0.66
     Miko
    0.65
    â̲
    0.63
    âĢİ
    0.63
     RHP
    0.63
    Activations Density 0.055%

    No Known Activations