INDEX

Explanations

references to coffee or coffee-related activities

oai_token-act-pair · gpt-3.5-turbo

mentions of coffee and coffee shops

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ROR

-0.89

oppable

-0.77

 Caldwell

-0.72

yss

-0.70

lihood

-0.70

Filename

-0.69

orse

-0.68

ukong

-0.67

 newcom

-0.65

veh

-0.64

POSITIVE LOGITS

 beans

1.23

 Beans

1.08

 bean

1.03

 brewed

1.02

 drinkers

0.90

 cups

0.89

 drip

0.88

 coffee

0.88

cake

0.87

nap

0.85

Activations Density 0.021%

references to coffee or coffee-related activities

mentions of coffee and coffee shops

No Comments

No Known Activations