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. 12091
    Prev
    Next
    INDEX
    Explanations

    instances of the word "dip"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dip" and its variations in various contexts

    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
    Reply
    -0.79
    Made
    -0.76
    fare
    -0.74
     Asylum
    -0.69
     WATCHED
    -0.67
    ÙIJ
    -0.66
     Machina
    -0.65
    scape
    -0.65
     Crusade
    -0.62
     Musical
    -0.62
    POSITIVE LOGITS
    shit
    1.19
     dipping
    1.15
    artisan
    1.03
    ients
    0.94
    iphany
    0.90
    irts
    0.90
    pty
    0.88
    psey
    0.88
     dip
    0.88
    aminer
    0.87
    Activations Density 0.014%

    No Known Activations