INDEX

Explanations

photographs or images

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

paces

-0.68

uits

-0.61

 grounding

-0.57

 Haku

-0.57

ights

-0.56

 crowds

-0.55

stood

-0.55

pow

-0.54

rouse

-0.54

»Ĵ

-0.54

POSITIVE LOGITS

 Continued

0.79

 Photo

0.73

 Advertisement

0.73

 Details

0.73

 Source

0.71

 Provided

0.69

 Highlights

0.68

 Related

0.66

Image

0.66

 Transcript

0.66

Activations Density 0.756%

photographs or images

No Comments

No Known Activations