INDEX

Explanations

the word "too" used in various contexts

oai_token-act-pair · gpt-3.5-turbo

phrases containing the word "too" and associated modifiers hinting at excess or emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

izen

-0.62

jri

-0.61

engers

-0.61

 highs

-0.60

 appro

-0.58

 embark

-0.57

apons

-0.57

plates

-0.56

 trending

-0.55

 Alley

-0.55

POSITIVE LOGITS

©¶æ¥µ

0.75

rame

0.74

esta

0.66

Ĥ¬

0.65

ĨĴ

0.63

Â·Â·

0.62

atio

0.61

GH

0.61

Ĥ

0.61

eming

0.59

Activations Density 0.207%

the word "too" used in various contexts

phrases containing the word "too" and associated modifiers hinting at excess or emphasis

No Comments

No Known Activations