INDEX

Explanations

phrases related to specific entities or concepts

oai_token-act-pair · gpt-3.5-turbo

the definite article "the."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ò

-0.81

thood

-0.77

elaide

-0.74

 because

-0.72

leground

-0.72

aba

-0.71

eno

-0.68

!!!!

-0.66

arate

-0.66

rage

-0.65

POSITIVE LOGITS

resa

1.07

 simplest

1.04

 slightest

1.02

 biggest

1.02

oret

1.00

 latter

0.99

 vast

0.98

 majority

0.98

 entire

0.98

 oldest

0.97

Activations Density 0.256%

phrases related to specific entities or concepts

the definite article "the."

No Comments

No Known Activations