INDEX

Explanations

superlatives or intensifiers conveying a high level of extremity

oai_token-act-pair · gpt-3.5-turbo

expressions of enthusiasm or high praise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Seym

-0.75

Reloaded

-0.75

edIn

-0.70

 Transcript

-0.69

 Lauder

-0.69

 Supported

-0.66

 Anger

-0.66

 Qiao

-0.65

endor

-0.63

 Frie

-0.63

POSITIVE LOGITS

imposed

1.31

nova

1.24

visor

1.14

charged

1.11

cedes

1.08

powers

1.03

computer

0.97

charg

0.94

visory

0.94

charging

0.92

Activations Density 0.014%

superlatives or intensifiers conveying a high level of extremity

expressions of enthusiasm or high praise

No Comments

No Known Activations