INDEX

Explanations

phrases related to dependency or necessity

oai_token-act-pair · gpt-3.5-turbo

references to dependency or necessity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

-0.78

ashtra

-0.76

ccording

-0.71

soDeliveryDate

-0.69

wic

-0.66

DAY

-0.66

MAC

-0.65

WARD

-0.64

MAP

-0.63

ently

-0.62

POSITIVE LOGITS

 anymore

0.93

 altogether

0.90

 permission

0.83

 distractions

0.80

 restraints

0.80

 knowledge

0.75

 slightest

0.74

 whatsoever

0.73

 safeguards

0.73

 pesky

0.71

Activations Density 0.219%

phrases related to dependency or necessity

references to dependency or necessity

No Comments

No Known Activations