INDEX

Explanations

mentions of the word "Am" combined with positive sentiment

oai_token-act-pair · gpt-3.5-turbo

the repeated mention of "Am."

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

ãģį

-0.74

 directions

-0.73

 masks

-0.66

elsius

-0.66

 corners

-0.66

theless

-0.65

 edges

-0.65

 tobacco

-0.65

vous

-0.65

ttes

-0.65

POSITIVE LOGITS

ethyst

1.27

endment

1.20

sterdam

1.19

ulet

1.16

bitious

1.11

ajor

1.08

itan

1.01

nesty

1.01

ateur

0.97

nesia

0.96

Activations Density 0.019%

mentions of the word "Am" combined with positive sentiment

the repeated mention of "Am."

No Comments

No Known Activations