INDEX

Explanations

phrases indicating awareness or prior knowledge of something

oai_token-act-pair · gpt-3.5-turbo

phrases indicating audience engagement or recognition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Flag

-0.66

 ransom

-0.63

 merger

-0.61

 fortun

-0.59

 trump

-0.59

 weap

-0.59

Fal

-0.58

 cardinal

-0.58

 Faust

-0.58

é¾įå¥ĳå£«

-0.57

POSITIVE LOGITS

 noticed

0.93

swer

0.92

 yourselves

0.91

 WATCHED

0.90

isode

0.85

taboola

0.81

 guessed

0.81

 reading

0.79

arten

0.79

 NOTICE

0.77

Activations Density 0.286%

phrases indicating awareness or prior knowledge of something

phrases indicating audience engagement or recognition

No Comments

No Known Activations