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. 12130
    Prev
    Next
    INDEX
    Explanations

    words related to submitting applications or requests

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "apply for" in various contexts

    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
    pod
    -0.77
    ofi
    -0.75
    Pod
    -0.74
    CG
    -0.74
     GOODMAN
    -0.74
    edge
    -0.71
    LAB
    -0.70
    ÄŁ
    -0.70
    é¾
    -0.70
    forward
    -0.68
    POSITIVE LOGITS
    gery
    1.01
     clarification
    0.92
    bidden
    0.84
     sale
    0.83
     inclusion
    0.83
     deletion
    0.82
     voluntary
    0.81
     permission
    0.80
     renewal
    0.78
    geries
    0.78
    Activations Density 0.109%

    No Known Activations