INDEX

Explanations

negative sentiments or actions directed towards specific groups or individuals

oai_token-act-pair · gpt-3.5-turbo

words reflecting strong emotions or actions related to negativity and conflict

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

 conclud

-0.61

enegger

-0.60

pherd

-0.59

 Carbuncle

-0.59

uana

-0.55

allery

-0.53

Ern

-0.52

Ħ¢

-0.52

leon

-0.51

rul

-0.51

POSITIVE LOGITS

pes

0.64

ickets

0.57

isively

0.56

heartedly

0.55

bugs

0.55

BT

0.53

Ts

0.52

bryce

0.52

ans

0.51

actively

0.51

Activations Density 0.706%

negative sentiments or actions directed towards specific groups or individuals

words reflecting strong emotions or actions related to negativity and conflict

No Comments

No Known Activations