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. 993
    Prev
    Next
    INDEX
    Explanations

    phrases related to infrastructure and technical systems

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to power infrastructure and data management

    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
    Brother
    -0.73
    ALLY
    -0.63
    Hum
    -0.62
    Veter
    -0.60
    Spl
    -0.59
     Youth
    -0.59
    Revolution
    -0.58
    Cash
    -0.57
    Phys
    -0.57
    OOOO
    -0.57
    POSITIVE LOGITS
    mith
    1.22
    poons
    1.21
    paces
    1.06
    pread
    1.06
    etting
    1.03
    ilver
    1.03
    hips
    1.02
    aurus
    1.01
    hare
    1.00
    hip
    1.00
    Activations Density 0.561%

    No Known Activations