INDEX

Explanations

references to the publication "Express."

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ellen

-0.75

aeper

-0.70

rost

-0.63

ategory

-0.62

 mars

-0.62

onies

-0.62

laus

-0.61

idding

-0.61

ASC

-0.61

vae

-0.61

POSITIVE LOGITS

Express

1.12

Route

1.03

 Express

0.92

ãĥ¼ãĥĨãĤ£

0.90

express

0.85

ions

0.84

ibe

0.78

Train

0.77

urance

0.77

ional

0.77

Activations Density 0.011%

references to the publication "Express."

mentions of the word "Express" in various contexts

No Comments

No Known Activations