INDEX

Explanations

comparative words or phrases

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_fs768-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

768

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

mberg

-0.61

EP

-0.59

ãĤ±

-0.58

xtap

-0.58

DC

-0.57

SEA

-0.54

 Advisory

-0.54

ayne

-0.53

Ctrl

-0.53

isha

-0.53

POSITIVE LOGITS

 than

2.15

than

2.08

 Than

1.71

iating

0.95

iator

0.78

 Faster

0.77

 behaved

0.76

 versions

0.74

 suited

0.73

 "$:/

0.73

Activations Density 3.445%

comparative words or phrases

No Comments

No Known Activations