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. 0-RES-JB
    6. 16277
    Prev
    Next
    INDEX
    Explanations

    words related to cameras and photography

    oai_token-act-pair · gpt-3.5-turbo

    references to cameras

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dict
    -0.75
     Ernst
    -0.68
    elia
    -0.68
     Pharmaceutical
    -0.67
     Pharma
    -0.66
    fried
    -0.66
     Domain
    -0.66
    Capital
    -0.65
    akings
    -0.65
    utical
    -0.65
    POSITIVE LOGITS
     cam
    4.09
    cam
    2.40
     camel
    1.80
    Cam
    1.56
     Cam
    1.53
     comr
    1.48
     webcam
    1.47
     CAM
    1.23
     camera
    1.23
    camera
    1.19
    Activations Density 0.012%

    No Known Activations