INDEX

Explanations

phrases related to safety and caution

oai_token-act-pair · gpt-3.5-turbo

concepts related to safety and safe environments

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

lez

-0.83

xual

-0.72

erent

-0.69

Lenin

-0.66

 intensify

-0.65

yss

-0.65

*/(

-0.65

çīĪ

-0.63

rots

-0.62

AX

-0.61

POSITIVE LOGITS

ounters

0.70

 safe

0.69

iland

0.67

safe

0.65

dden

0.62

Safety

0.60

 Safe

0.60

 childbirth

0.59

glers

0.59

aband

0.58

Activations Density 0.264%

phrases related to safety and caution

concepts related to safety and safe environments

No Comments

No Known Activations