INDEX

Explanations

phrases indicating range or variation in quantities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

resy

-0.78

mone

-0.73

lees

-0.72

POST

-0.72

orsi

-0.70

icipated

-0.70

rition

-0.69

iquette

-0.67

nor

-0.65

itement

-0.64

POSITIVE LOGITS

 mildly

0.96

 mild

0.75

 afar

0.73

 innocuous

0.73

 quirky

0.71

 thinly

0.70

 humorous

0.70

 benign

0.70

 mundane

0.69

 outright

0.67

Activations Density 0.028%

phrases indicating range or variation in quantities

No Comments

No Known Activations