INDEX

Explanations

specific technical terms and phrases related to technology and online media

oai_token-act-pair · gpt-3.5-turbo

specific terms and phrases related to movies, culture, and community events

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

estate

-0.83

"]=>

-0.76

 Mehran

-0.74

allery

-0.70

']

-0.66

wagon

-0.64

grounds

-0.64

'/

-0.63

Reviewer

-0.61

SHIP

-0.61

POSITIVE LOGITS

 flourish

0.78

 lenses

0.68

 scissors

0.68

 torches

0.68

 gloves

0.67

 flowing

0.67

 hindsight

0.66

 abandon

0.65

 flair

0.65

 linem

0.63

Activations Density 1.068%

specific technical terms and phrases related to technology and online media

specific terms and phrases related to movies, culture, and community events

No Comments

No Known Activations