INDEX

Explanations

phrases that imply inquiry or confusion

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bara

-0.92

termination

-0.75

abase

-0.74

alore

-0.69

etheless

-0.69

perial

-0.67

chwitz

-0.66

anian

-0.66

farm

-0.66

terness

-0.66

POSITIVE LOGITS

Atk

0.72

Sort

0.69

 Sort

0.68

 Type

0.68

é¾įå

0.67

 Likes

0.65

 Bust

0.65

ivals

0.64

Prev

0.63

 Favorite

0.62

Activations Density 0.009%

phrases that imply inquiry or confusion

No Comments

No Known Activations