INDEX

Explanations

words related to recommendations or intentions

oai_token-act-pair · gpt-3.5-turbo

terms associated with recommendations, plans, and predictions

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

ĪĴ

-0.79

ertodd

-0.79

MENT

-0.76

Į

-0.75

erie

-0.75

OTO

-0.74

ntil

-0.74

kk

-0.74

oso

-0.72

mson

-0.70

POSITIVE LOGITS

 Parenthood

0.90

 amount

0.90

 timeframe

0.81

 timeline

0.80

 lifespan

0.80

 path

0.79

 outcome

0.79

 timetable

0.78

 number

0.77

 duration

0.76

Activations Density 0.114%

words related to recommendations or intentions

terms associated with recommendations, plans, and predictions

No Comments

No Known Activations