INDEX

Explanations

words related to qualities or attributes such as "purity" or "quality"

oai_token-act-pair · gpt-3.5-turbo

terms related to the concept of "identity."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

accompan

-0.85

soDeliveryDate

-0.68

 ellipt

-0.68

 referen

-0.65

hester

-0.64

Capt

-0.64

awaru

-0.62

prototype

-0.61

inav

-0.61

emetery

-0.61

POSITIVE LOGITS

ity

0.99

Peb

0.87

fulness

0.78

ilty

0.76

istically

0.74

lihood

0.74

yip

0.73

-------

0.71

ities

0.71

rics

0.70

Activations Density 0.017%

words related to qualities or attributes such as "purity" or "quality"

terms related to the concept of "identity."

No Comments

No Known Activations