© 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. 6489
    Prev
    Next
    INDEX
    Explanations

    the word "possible"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "possible" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    masters
    -0.93
    rix
    -0.85
    lua
    -0.83
    erie
    -0.80
    ulu
    -0.80
    ogun
    -0.80
    lite
    -0.79
    ogie
    -0.78
    cipline
    -0.78
    bane
    -0.78
    POSITIVE LOGITS
     inclusion
    0.81
     defect
    0.79
     embodiments
    0.79
     implication
    0.77
     inference
    0.77
     explanations
    0.75
     demise
    0.74
     outcomes
    0.74
     indication
    0.73
     exception
    0.72
    Activations Density 0.024%

    No Known Activations