INDEX

Explanations

countries and locations

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

tops

-0.66

Sym

-0.65

hide

-0.62

RTX

-0.60

atin

-0.60

Discussion

-0.59

 Weiner

-0.59

TY

-0.58

iple

-0.58

veyard

-0.57

POSITIVE LOGITS

 Airlines

0.97

 Today

0.88

's

0.85

 TODAY

0.84

 Yard

0.83

 invaded

0.81

 Arabia

0.77

 annexed

0.75

borg

0.74

 Aerospace

0.74

Activations Density 0.782%

countries and locations

No Comments

No Known Activations