© 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. 3-RES-JB
    11. 15443
    Prev
    Next
    INDEX
    Explanations

    the verb "doesn't", followed by the contraction "'t", combined with a negative action or result

    oai_token-act-pair · gpt-3.5-turbo

    instances of the contraction "don't."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebus
    -0.71
    aminer
    -0.68
     Seym
    -0.66
     looms
    -0.65
     imitation
    -0.63
     buggy
    -0.63
     XT
    -0.63
     mathemat
    -0.63
     carbohyd
    -0.62
     hemor
    -0.62
    POSITIVE LOGITS
    ï¸ı
    1.00
    女
    0.93
    ×Ķ
    0.91
    ATH
    0.89
    ··
    0.85
    ¯¯
    0.84
    Balt
    0.83
    ution
    0.81
    İ
    0.80
    âĸĦ
    0.79
    Activations Density 0.284%

    No Known Activations