© 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. 10-RES-JB
    11. 16961
    Prev
    Next
    INDEX
    Explanations

    time stamps indicating specific events or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to time and specific events

    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
     photoc
    -0.65
    ————
    -0.64
    iries
    -0.60
    ————————————————
    -0.58
     inval
    -0.57
    sheets
    -0.56
    apon
    -0.56
    olkien
    -0.56
    soType
    -0.55
    urat
    -0.55
    POSITIVE LOGITS
     Caption
    0.79
     VIDEOS
    0.77
    Photos
    0.73
     Replay
    0.71
    Audio
    0.70
    Hide
    0.66
     WATCHED
    0.63
    Video
    0.59
     Photos
    0.58
    MAN
    0.57
    Activations Density 0.047%

    No Known Activations