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. 22715
    Prev
    Next
    INDEX
    Explanations

    organizations, countries, or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific organizations, countries, and entities

    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
     ..."
    -0.59
    î
    -0.57
    åĤ
    -0.54
    Enlarge
    -0.51
    SAN
    -0.50
    ``
    -0.49
    ZI
    -0.47
    odox
    -0.47
    ãģĨ
    -0.47
    chest
    -0.47
    POSITIVE LOGITS
     cannot
    0.65
     countered
    0.64
     meanwhile
    0.64
     underwent
    0.63
     reverted
    0.63
     succeeded
    0.63
     fared
    0.62
     retains
    0.61
     lacks
    0.60
     also
    0.60
    Activations Density 1.060%

    No Known Activations