INDEX

Explanations

phrases related to being impressed by something

oai_token-act-pair · gpt-3.5-turbo

phrases that express amazement or admiration

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

isher

-0.76

 Supplement

-0.71

odder

-0.61

)]

-0.61

UME

-0.61

Ans

-0.60

 Myster

-0.60

oubt

-0.59

AGE

-0.58

iculture

-0.57

POSITIVE LOGITS

HCR

0.93

beit

0.89

ells

0.83

ling

0.82

ls

0.82

 much

0.81

lers

0.81

Sad

0.75

 MUCH

0.75

dy

0.73

Activations Density 0.068%

phrases related to being impressed by something

phrases that express amazement or admiration

No Comments

No Known Activations