© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 13027
    Prev
    Next
    INDEX
    Explanations

    mentions of cameras, particularly in the context of discussions or opinions about their use, effectiveness, or installation

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of cameras in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nant
    -0.78
    itable
    -0.76
    emonic
    -0.75
    thritis
    -0.74
    heit
    -0.72
    adder
    -0.72
    fy
    -0.71
    luent
    -0.71
    inence
    -0.69
    erd
    -0.68
    POSITIVE LOGITS
     cameras
    1.36
     Camer
    1.35
     microphones
    1.13
     camera
    1.06
     Camera
    0.90
     recorder
    0.82
    ynthesis
    0.82
     pans
    0.80
     microphone
    0.79
    Camera
    0.79
    Activations Density 0.009%

    No Known Activations