© 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. 22578
    Prev
    Next
    INDEX
    Explanations

    locations or names related to the name "Chandler"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals

    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
    estones
    -1.02
    estone
    -0.92
    glers
    -0.89
    ctions
    -0.86
    incinn
    -0.82
    utions
    -0.80
    CLE
    -0.77
    ulously
    -0.76
    undai
    -0.75
    atable
    -0.73
    POSITIVE LOGITS
     Chandler
    0.78
     Sinclair
    0.74
     Carlson
    0.73
     Dempsey
    0.70
     Clayton
    0.69
    iasis
    0.69
     Randolph
    0.68
     Jensen
    0.68
     Howard
    0.68
     Grayson
    0.68
    Activations Density 0.020%

    No Known Activations