INDEX

Explanations

the word "ether" in various contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of variations of the word "ether."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ELS

-0.78

 Strauss

-0.65

zza

-0.65

====

-0.63

========

-0.62

============

-0.62

 deaf

-0.61

WS

-0.60

selage

-0.60

 fries

-0.59

POSITIVE LOGITS

apy

1.50

swer

1.16

1.07

apist

1.07

idge

1.06

sburg

1.05

iated

1.00

nian

0.97

spr

0.95

mal

0.93

Activations Density 0.022%

the word "ether" in various contexts

occurrences of variations of the word "ether."

No Comments

No Known Activations