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. 6-RES-JB
    6. 8948
    Prev
    Next
    INDEX
    Explanations

    IP addresses and URLs

    oai_token-act-pair · gpt-3.5-turbo

    patterns and references related to internet addresses and URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unfold
    -0.80
     gearing
    -0.78
    OIL
    -0.74
     rive
    -0.73
     coating
    -0.71
     drastic
    -0.70
     omission
    -0.70
     paralysis
    -0.70
     leaps
    -0.69
     sleeves
    -0.69
    POSITIVE LOGITS
    localhost
    1.34
    domain
    1.23
    username
    1.10
    password
    1.09
    example
    1.05
    USER
    1.03
    foo
    1.02
    server
    1.01
    address
    0.99
    host
    0.98
    Activations Density 0.158%

    No Known Activations