© 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. 13825
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to extraordinary or remarkable events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to obstacles and challenges

    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
    ;;;;;;;;
    -0.85
    ACTED
    -0.72
    $$$$
    -0.70
    ergy
    -0.70
     consent
    -0.67
     Mens
    -0.66
     Instr
    -0.65
    cedented
    -0.63
    ership
    -0.63
    National
    -0.63
    POSITIVE LOGITS
    acle
    1.24
    acles
    1.19
    opus
    0.87
    veyard
    0.86
     Pwr
    0.77
    cock
    0.75
    emis
    0.75
    culus
    0.75
    ylon
    0.73
    ifix
    0.73
    Activations Density 0.014%

    No Known Activations