INDEX

Explanations

verbs related to actions or decisions

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

Not in Any Lists

No Comments

Negative Logits

UTH

-0.70

 Returning

-0.67

por

-0.67

voy

-0.62

ipel

-0.60

diagn

-0.59

war

-0.58

 Examination

-0.58

 Returns

-0.58

transfer

-0.57

POSITIVE LOGITS

soever

1.18

 happens

0.85

 happened

0.77

 they

0.76

 else

0.75

 mattered

0.73

necessary

0.72

 bothers

0.69

andom

0.68

 amounted

0.68

Activations Density 0.029%

verbs related to actions or decisions

No Comments

No Known Activations