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. 8716
    Prev
    Next
    INDEX
    Explanations

    references to camping

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "camp" in various contexts

    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
    lihood
    -0.72
     regress
    -0.70
    ctive
    -0.67
    piring
    -0.67
     platinum
    -0.64
     nutrit
    -0.63
    ĸļ
    -0.63
    hm
    -0.63
     wip
    -0.62
     toget
    -0.60
    POSITIVE LOGITS
    fires
    1.12
    ground
    1.11
    fire
    1.06
    grounds
    1.03
    camp
    0.99
     camp
    0.97
    agna
    0.97
    agne
    0.91
    hor
    0.88
    aign
    0.85
    Activations Density 0.010%

    No Known Activations