INDEX

Explanations

phrases related to activism and protests

oai_token-act-pair · gpt-3.5-turbo

phrases related to protests and activism against various issues

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

 saliva

-0.72

fab

-0.70

 glances

-0.70

 altogether

-0.69

 liner

-0.69

 Paddock

-0.68

 tasted

-0.66

cking

-0.66

 drawer

-0.65

 caveat

-0.65

POSITIVE LOGITS

 boycot

0.88

 advoc

0.87

 boycott

0.84

independence

0.82

 behalf

0.78

 advocating

0.77

cot

0.77

 independence

0.74

enegger

0.74

orses

0.74

Activations Density 0.277%

phrases related to activism and protests

phrases related to protests and activism against various issues

No Comments

No Known Activations