INDEX

Explanations

verbs related to taking action or making changes

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

starter

-0.63

abet

-0.62

sa

-0.61

ija

-0.61

raltar

-0.61

spot

-0.61

den

-0.60

ahoo

-0.60

mad

-0.59

 topped

-0.59

POSITIVE LOGITS

ulate

0.96

 them

0.92

orously

0.88

uate

0.87

ively

0.86

 their

0.85

ibly

0.84

our

0.81

 oneself

0.81

 themselves

0.78

Activations Density 3.061%

verbs related to taking action or making changes

No Comments

No Known Activations