Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 23945
    Prev
    Next
    INDEX
    Explanations

    words related to bodies of water

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pond" and its variations in context

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

    No Comments

    Negative Logits
     millenn
    -0.67
    Rated
    -0.66
     Universities
    -0.64
     airlines
    -0.63
     universities
    -0.63
     flight
    -0.62
    dos
    -0.62
     incap
    -0.61
    ãģĦ
    -0.61
     attorneys
    -0.60
    POSITIVE LOGITS
    ering
    1.12
    ered
    0.99
     pond
    0.96
    esville
    0.94
    SourceFile
    0.91
    erer
    0.88
    rast
    0.84
    ers
    0.84
    isher
    0.83
    issance
    0.83
    Activations Density 0.008%

    No Known Activations