INDEX

Explanations

verbs that imply imposition or control over others

oai_token-act-pair · gpt-3.5-turbo

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ovember

-0.83

bucks

-0.77

athan

-0.77

nih

-0.76

Champ

-0.69

Ã£o

-0.69

opsy

-0.68

enth

-0.68

itu

-0.67

atform

-0.67

POSITIVE LOGITS

 dictates

1.13

 dictate

1.05

 dictated

0.99

 dict

0.98

rules

0.96

 rules

0.92

 enforced

0.91

 governs

0.87

 guidelines

0.86

 forbid

0.85

Activations Density 0.085%

verbs that imply imposition or control over others

No Known Activations