INDEX

Explanations

specific language identifiers or classifiers associated with cultural contexts

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

-0.72

 favor

-0.71

 favour

-0.66

 juggling

-0.65

 accompl

-0.64

cloth

-0.63

 Franch

-0.63

gag

-0.62

itaire

-0.62

 Pathfinder

-0.61

POSITIVE LOGITS

Ŀ

1.27

Ĩ

1.18

¹

1.14

ķ

1.11

ĭ

1.08

¶

1.07

Ĥ¬

1.05

§

1.03

ĺ

1.00

¦

0.99

Activations Density 0.002%

specific language identifiers or classifiers associated with cultural contexts

No Comments

No Known Activations