© 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. 2-RES-JB
    11. 12510
    Prev
    Next
    INDEX
    Explanations

    references to a specific name 'Dorner'

    oai_token-act-pair · gpt-3.5-turbo

    references to an individual named Dor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.95
    unct
    -0.72
    WAYS
    -0.71
     Terrorism
    -0.69
    heet
    -0.66
     HuffPost
    -0.65
    BRE
    -0.65
    tenance
    -0.63
     Wanted
    -0.63
    unction
    -0.63
    POSITIVE LOGITS
    ÃŃa
    0.93
    iane
    0.93
    je
    0.91
    ado
    0.90
     Dor
    0.90
    cas
    0.88
    oshenko
    0.86
    chester
    0.85
    rance
    0.84
    idad
    0.82
    Activations Density 0.004%

    No Known Activations