© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 502
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the character "Lex Luthor"

    oai_token-act-pair · gpt-3.5-turbo

    references to the character Lex Luthor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imental
    -0.73
    theless
    -0.71
    wich
    -0.70
    fc
    -0.69
    backer
    -0.69
    RAFT
    -0.68
    nels
    -0.67
     glacier
    -0.66
    bone
    -0.66
    deen
    -0.65
    POSITIVE LOGITS
     Lex
    3.86
    Lex
    3.34
     lex
    2.05
     Nex
    1.63
     Luthor
    1.43
     Lexington
    1.25
     Lear
    1.16
     Lys
    1.13
     Krypt
    1.08
     Lois
    1.04
    Activations Density 0.010%

    No Known Activations