INDEX

Explanations

ordinal indicators or rankings in numerical form

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

worms

-0.77

politics

-0.67

rooms

-0.67

»Ĵ

-0.66

ugs

-0.65

helps

-0.65

maps

-0.63

zilla

-0.63

ãĤĭ

-0.62

bda

-0.61

POSITIVE LOGITS

 highest

1.20

 largest

1.20

 tallest

1.14

 busiest

1.12

 oldest

1.11

 fastest

1.09

 richest

1.06

 cheapest

1.06

highest

1.01

 smartest

1.01

Activations Density 0.042%

ordinal indicators or rankings in numerical form

No Comments

No Known Activations