INDEX

Explanations

phrases indicating future action or plans

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "have" 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 @ 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

 guiName

-0.61

osi

-0.61

 disguise

-0.60

 hostage

-0.58

 rumor

-0.57

 wounding

-0.55

andan

-0.55

arming

-0.54

 mash

-0.54

 currently

-0.53

POSITIVE LOGITS

 been

1.03

 gotten

0.98

been

0.94

 gone

0.91

 undergone

0.87

stood

0.85

 taken

0.85

 eaten

0.84

 begun

0.83

gotten

0.81

Activations Density 0.060%

phrases indicating future action or plans

occurrences of the word "have" in various contexts

No Comments

No Known Activations