INDEX

Explanations

words related to concerns or worries

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

nice

-0.74

ingers

-0.74

lite

-0.70

ples

-0.61

ophone

-0.61

 handy

-0.60

iller

-0.58

unes

-0.58

dating

-0.58

 slick

-0.57

POSITIVE LOGITS

warts

1.06

wart

1.04

lessly

0.91

 about

0.85

 trolling

0.84

ingly

0.82

 bells

0.81

ieties

0.80

 ABOUT

0.77

 regarding

0.76

Activations Density 0.532%

words related to concerns or worries

No Comments

No Known Activations