INDEX

Explanations

mentions of coffee-related places or activities

oai_token-act-pair · gpt-3.5-turbo

references to coffee and coffee-related establishments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

-0.86

yss

-0.78

avid

-0.77

alez

-0.74

 newcom

-0.70

omething

-0.67

imedia

-0.66

abama

-0.66

oppable

-0.65

umbn

-0.65

POSITIVE LOGITS

 beans

1.38

 Beans

1.12

 bean

1.11

 brewed

1.11

 cups

1.07

 drinkers

1.03

 coffee

1.01

cup

1.00

 shops

0.95

houses

0.94

Activations Density 0.029%

mentions of coffee-related places or activities

references to coffee and coffee-related establishments

No Comments

No Known Activations