INDEX

Explanations

mentions of the publication "Express" in various contexts

oai_token-act-pair · gpt-3.5-turbo

the repeated mention of "Express" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.4.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

aeper

-0.80

ellen

-0.76

 Ambro

-0.71

abama

-0.69

kees

-0.66

quartered

-0.62

ographical

-0.62

laus

-0.62

STEM

-0.61

antically

-0.61

POSITIVE LOGITS

Route

1.14

ions

1.02

Express

0.99

ivity

0.91

ãĥ¼ãĥĨãĤ£

0.87

ional

0.86

VPN

0.83

Poll

0.77

way

0.77

 Express

0.74

Activations Density 0.013%

mentions of the publication "Express" in various contexts

the repeated mention of "Express" in various contexts

No Comments

No Known Activations