INDEX

Explanations

comparative words and phrases focusing on improvement

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

EVA

-0.68

ainted

-0.67

shire

-0.65

EP

-0.64

mberg

-0.64

vp

-0.64

sm

-0.61

odor

-0.60

aly

-0.60

ayne

-0.59

POSITIVE LOGITS

 than

1.82

 Than

1.58

than

1.56

iating

1.00

 "$:/

0.87

 behaved

0.84

 versions

0.83

iator

0.82

iation

0.81

 suited

0.75

Activations Density 0.906%

comparative words and phrases focusing on improvement

No Comments

No Known Activations