Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 14258
    Prev
    Next
    INDEX
    Explanations

    events or actions that have been recorded on some form of camera or video

    oai_token-act-pair · gpt-3.5-turbo

    instances of actions or events that are recorded or observed on video or camera

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hesda
    -0.86
    ocations
    -0.75
    heon
    -0.72
    uliffe
    -0.72
    cellence
    -0.71
    jobs
    -0.70
    Suggest
    -0.70
    ¯¯
    -0.68
    bush
    -0.68
    ¯¯¯¯
    -0.68
    POSITIVE LOGITS
     CCTV
    1.77
     surveillance
    1.49
     camera
    1.49
     cameras
    1.48
     webcam
    1.45
     videot
    1.34
     cellphone
    1.31
     footage
    1.31
     radar
    1.21
     television
    1.20
    Activations Density 0.256%

    No Known Activations