© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 12597
    Prev
    Next
    INDEX
    Explanations

    phrases related to instructions or directives starting with the word "don't"

    oai_token-act-pair · gpt-3.5-turbo

    the word "don'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 @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     afore
    -0.75
     Dise
    -0.74
    DEP
    -0.69
    pha
    -0.67
     VERS
    -0.65
     CONTROL
    -0.64
     Amph
    -0.63
    paio
    -0.63
    Software
    -0.63
    ossibility
    -0.63
    POSITIVE LOGITS
    't
    1.27
    atives
    1.00
    uts
    0.93
    ates
    0.91
    ned
    0.89
    ning
    0.81
    kie
    0.79
    nell
    0.78
    nie
    0.77
    iors
    0.76
    Activations Density 0.099%

    No Known Activations