© 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. 4-RES-JB
    11. 7283
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Colin."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the name "Colin" in various contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cffff
    -0.96
    gency
    -0.74
    stroke
    -0.71
    ansas
    -0.70
    hips
    -0.70
    TOP
    -0.69
    hots
    -0.68
    ItemTracker
    -0.67
    framework
    -0.67
    shapeshifter
    -0.67
    POSITIVE LOGITS
     Kaepernick
    1.10
     Powell
    1.08
     Greenwood
    0.95
     Uz
    0.81
     Campbell
    0.78
     Moran
    0.78
    otte
    0.76
     Colin
    0.76
    osure
    0.75
    ophon
    0.75
    Activations Density 0.010%

    No Known Activations