INDEX

Explanations

words related to significant negative reactions or emotions

oai_token-act-pair · gpt-3.5-turbo

words associated with negative emotional reactions or social unrest

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 carrot

-0.65

 fucked

-0.61

ĪĴ

-0.60

©¶æ

-0.60

 violet

-0.59

 compliment

-0.56

 fing

-0.56

 alphabet

-0.56

 corpse

-0.53

cknow

-0.52

POSITIVE LOGITS

 amongst

1.01

 among

0.99

among

0.86

lees

0.74

 akin

0.71

 elsewhere

0.70

 throughout

0.70

 domestically

0.69

 internationally

0.69

 across

0.68

Activations Density 0.283%

words related to significant negative reactions or emotions

words associated with negative emotional reactions or social unrest

No Comments

No Known Activations