INDEX

Explanations

phrases related to problems, danger, harm, and injuries

oai_token-act-pair · gpt-3.5-turbo

terms related to safety concerns and injuries

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

ku

-0.88

kt

-0.76

liam

-0.71

kus

-0.70

ãĤ©

-0.70

kh

-0.67

utm

-0.66

bal

-0.65

last

-0.65

 Loft

-0.64

POSITIVE LOGITS

nor

1.01

 whatsoever

0.95

 anymore

0.89

erno

0.71

 anywhere

0.63

ocard

0.61

 detectable

0.60

 temptation

0.60

 Spray

0.60

 slightest

0.58

Activations Density 0.870%

phrases related to problems, danger, harm, and injuries

terms related to safety concerns and injuries

No Comments

No Known Activations