INDEX

Explanations

questions beginning with "What do you" or "How do you"

oai_token-act-pair · gpt-3.5-turbo

interrogative phrases that begin with "What do you"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Reviewer

-0.83

workshop

-0.77

ntil

-0.73

ufact

-0.69

boarding

-0.68

mobi

-0.67

 ridden

-0.66

haul

-0.65

creen

-0.63

anmar

-0.62

POSITIVE LOGITS

omsday

1.14

herty

0.86

zens

0.85

 impressions

0.77

ppel

0.77

atives

0.74

ggies

0.73

xx

0.73

 things

0.72

uts

0.72

Activations Density 0.040%

questions beginning with "What do you" or "How do you"

interrogative phrases that begin with "What do you"

No Comments

No Known Activations