INDEX

Explanations

phrases related to business collaborations or agreements

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "partnership" or related terms indicating collaboration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

metics

-0.77

hma

-0.77

raq

-0.75

gor

-0.74

ma

-0.73

cho

-0.72

eared

-0.70

severe

-0.70

gun

-0.70

ghazi

-0.69

POSITIVE LOGITS

 partner

1.11

 between

1.06

 partners

0.98

 partnership

0.95

 agreement

0.91

 relationship

0.86

 partnerships

0.85

 agreements

0.84

BET

0.82

 alliance

0.79

Activations Density 0.067%

phrases related to business collaborations or agreements

occurrences of the word "partnership" or related terms indicating collaboration

No Comments

No Known Activations