INDEX

Explanations

places or settings within a text

oai_token-act-pair · gpt-3.5-turbo

prepositions and phrases indicating location or context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Challenges

-0.69

 Janeiro

-0.68

 Rica

-0.67

 Puzzles

-0.67

enegger

-0.65

NAD

-0.63

 Purs

-0.62

abwe

-0.61

 Chero

-0.61

éģ

-0.61

POSITIVE LOGITS

cast

0.96

usal

0.95

erb

0.84

vern

0.80

ork

0.79

harm

0.79

alter

0.76

usive

0.75

âĢĳ

0.74

hist

0.74

Activations Density 0.242%

places or settings within a text

prepositions and phrases indicating location or context

No Comments

No Known Activations