INDEX

Explanations

phrases related to activities or events that happen behind the scenes

oai_token-act-pair · gpt-3.5-turbo

references to "behind the scenes" activities or situations

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

mington

-0.84

nesota

-0.83

liam

-0.83

heit

-0.80

fect

-0.78

haps

-0.77

INGS

-0.74

gary

-0.74

arcity

-0.74

ŃĶ

-0.73

POSITIVE LOGITS

 workings

0.78

 filming

0.76

 mach

0.74

 scenes

0.72

 talents

0.71

 development

0.69

 knowledge

0.68

 insider

0.67

 footage

0.65

 reconnaissance

0.64

Activations Density 0.052%

phrases related to activities or events that happen behind the scenes

references to "behind the scenes" activities or situations

No Comments

No Known Activations