© 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. 6-RES-JB
    11. 12099
    Prev
    Next
    INDEX
    Explanations

    video-related cues or instructions

    oai_token-act-pair · gpt-3.5-turbo

    references to watching videos or content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ctrl
    -0.91
    phi
    -0.76
    jury
    -0.71
    sembly
    -0.67
    interstitial
    -0.66
    ãĥ´
    -0.65
    VEN
    -0.63
     rhy
    -0.62
    bably
    -0.61
     lettuce
    -0.60
    POSITIVE LOGITS
    tower
    1.28
     Watching
    1.10
    dog
    1.05
    dogs
    0.97
    ing
    0.85
    imon
    0.84
    watch
    0.83
    points
    0.81
    watching
    0.80
     Watch
    0.79
    Activations Density 0.020%

    No Known Activations