INDEX

Explanations

phrases related to stories or events happening outside a specific location or situation

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

anche

-0.92

onder

-0.81

oka

-0.80

ulous

-0.79

oleon

-0.77

eday

-0.76

enegger

-0.75

lda

-0.73

ander

-0.73

anches

-0.69

POSITIVE LOGITS

 linebacker

0.74

 patio

0.69

 world

0.68

world

0.68

 worlds

0.67

 perimeter

0.66

shock

0.66

wards

0.65

 diameter

0.65

 adolesc

0.65

Activations Density 0.464%

phrases related to stories or events happening outside a specific location or situation

No Comments

No Known Activations