© 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. 1-RES-JB
    11. 10277
    Prev
    Next
    INDEX
    Explanations

    contractions where the word "don't" immediately precedes a verb

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "didn't" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    armed
    -0.82
    phant
    -0.74
     Duty
    -0.67
     Dise
    -0.65
     DRAGON
    -0.65
    capacity
    -0.64
    mania
    -0.63
     duty
    -0.62
     ILCS
    -0.61
     Mant
    -0.60
    POSITIVE LOGITS
    't
    1.36
    ":"/
    0.86
    nt
    0.81
    ajor
    0.76
     bother
    0.74
    ijah
    0.73
    etsk
    0.72
    ÃĥÃĤ
    0.71
    ettings
    0.70
    ÃŃ
    0.70
    Activations Density 0.029%

    No Known Activations