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. 7-RES-JB
    6. 3378
    Prev
    Next
    INDEX
    Explanations

    words related to checking and maintaining something in a specific condition

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to maintaining order or control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.87
    ĪĴ
    -0.84
     DRAG
    -0.73
    elson
    -0.71
    çīĪ
    -0.70
    haps
    -0.70
     PRESIDENT
    -0.69
    OME
    -0.67
    OPLE
    -0.66
    ogyn
    -0.65
    POSITIVE LOGITS
     wraps
    0.86
     Nightmares
    0.78
     tighter
    0.76
     tight
    0.74
     suspense
    0.74
     secrecy
    0.71
     refriger
    0.70
    clud
    0.69
    hum
    0.69
     perpetual
    0.69
    Activations Density 0.115%

    No Known Activations