INDEX

Explanations

mentions of the automobile brand "Honda"

oai_token-act-pair · gpt-3.5-turbo

mentions of the brand Honda and its models

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

ablishment

-0.93

 Seym

-0.86

acular

-0.85

asure

-0.81

orial

-0.80

byter

-0.78

vironment

-0.77

ngth

-0.77

tle

-0.75

yip

-0.74

POSITIVE LOGITS

 Civic

1.03

 Accord

0.88

 Motor

0.81

 Honda

0.80

 Odyssey

0.75

 Karin

0.73

 Rouse

0.70

uana

0.69

asaki

0.68

ity

0.68

Activations Density 0.020%

mentions of the automobile brand "Honda"

mentions of the brand Honda and its models

No Comments

No Known Activations