© 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. 17598
    Prev
    Next
    INDEX
    Explanations

    mentions of creators or authors

    oai_token-act-pair · gpt-3.5-turbo

    references to creators or individuals who produce content

    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
    abb
    -0.77
    vor
    -0.74
    olit
    -0.70
    ibaba
    -0.65
    olk
    -0.65
    alsa
    -0.63
     Clin
    -0.62
    etta
    -0.61
     Rite
    -0.59
     Spa
    -0.59
    POSITIVE LOGITS
     creator
    1.04
    creator
    1.03
     creators
    0.97
    ãĥķãĤ¡
    0.90
     laureate
    0.88
    caster
    0.84
    ãĤº
    0.84
     extraord
    0.82
     Creat
    0.79
    ãĤ©
    0.78
    Activations Density 0.013%

    No Known Activations