© 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. 7389
    Prev
    Next
    INDEX
    Explanations

    words related to a person named Ter(se) in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    variations of the suffix "ter" or similar phonetic patterns

    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
     innocence
    -0.68
    ortium
    -0.67
    ruary
    -0.67
     knees
    -0.66
     corp
    -0.65
     sake
    -0.63
     solvent
    -0.63
    rency
    -0.62
     slightest
    -0.62
     baptism
    -0.61
    POSITIVE LOGITS
    xual
    0.82
    lake
    0.81
    apes
    0.80
    oxide
    0.79
    English
    0.74
    INAL
    0.74
    othy
    0.73
     Kahn
    0.72
    POSE
    0.71
    âĶĢâĶĢâĶĢâĶĢ
    0.71
    Activations Density 0.152%

    No Known Activations