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

    Neuronpedia

    Jacobian LensNEW
    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. 16695
    Prev
    Next
    INDEX
    Explanations

    various types of reports or observations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of visual phenomena or descriptions of sights

    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
    ĸļ
    -0.84
    ruary
    -0.78
    utics
    -0.73
    ptroller
    -0.73
     Ethics
    -0.72
    justice
    -0.72
    Polit
    -0.71
    respect
    -0.71
    adr
    -0.71
    priv
    -0.70
    POSITIVE LOGITS
     sightings
    1.36
     UFOs
    1.22
     earthquakes
    1.21
     debris
    1.21
     sighting
    1.20
     flares
    1.19
     disturbances
    1.15
     explosions
    1.15
     phenomena
    1.14
     anomal
    1.14
    Activations Density 0.748%

    No Known Activations