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. 561
    Prev
    Next
    INDEX
    Explanations

    phrases including the word "community"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "com" within words

    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
     Krug
    -0.63
     Wilde
    -0.63
     Refuge
    -0.63
     steroids
    -0.62
     AFL
    -0.59
     recall
    -0.59
     Ducks
    -0.59
    514
    -0.58
     Wings
    -0.57
     Flan
    -0.57
    POSITIVE LOGITS
    pleted
    1.31
    fortable
    1.27
    puters
    1.26
    pleting
    1.13
    pletion
    1.11
    puting
    1.10
    mitted
    1.02
    mented
    0.99
    edy
    0.97
    parable
    0.96
    Activations Density 0.024%

    No Known Activations