INDEX

Explanations

the word "and" in the text

oai_token-act-pair · gpt-3.5-turbo

the conjunction "and" 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

è»

-0.70

æĥ

-0.64

edIn

-0.63

æµ

-0.63

éŃĶ

-0.61

çĲ

-0.59

NULL

-0.59

 Leilan

-0.58

ãĥĩãĤ£

-0.58

zona

-0.58

POSITIVE LOGITS

rogen

0.84

rogens

0.78

 then

0.76

 consequently

0.75

 therefore

0.75

 thus

0.72

 hence

0.66

0.65

hra

0.61

 possibly

0.61

Activations Density 0.409%

the word "and" in the text

the conjunction "and" in various contexts

No Comments

No Known Activations