INDEX

Explanations

phrases related to conflicts or disputes between parties

oai_token-act-pair · gpt-3.5-turbo

terms and phrases related to conflicts or arguments

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eele

-0.84

iaries

-0.72

akeru

-0.71

undai

-0.71

 stocking

-0.71

urus

-0.63

 footprints

-0.60

icrobial

-0.60

CHO

-0.59

extra

-0.59

POSITIVE LOGITS

 between

1.19

 raging

1.08

 raged

1.03

 waged

0.98

 ensued

0.98

between

0.98

roy

0.91

 erupted

0.91

 involving

0.90

 brewing

0.90

Activations Density 0.242%

phrases related to conflicts or disputes between parties

terms and phrases related to conflicts or arguments

No Comments

No Known Activations