INDEX

Explanations

phrases related to avoiding potential negative outcomes

oai_token-act-pair · gpt-3.5-turbo

phrases related to avoiding negative outcomes or risks

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

soDeliveryDate

-0.81

 largeDownload

-0.77

REL

-0.71

çľ

-0.65

 Shap

-0.65

é¾įåĸļå£«

-0.65

 Compass

-0.63

å¦

-0.62

 Frontier

-0.61

ãģ®é

-0.60

POSITIVE LOGITS

 altogether

1.07

 pitfalls

1.06

 harm

0.94

 costly

0.84

 misuse

0.83

 temptation

0.82

 harmful

0.82

 bloodshed

0.82

 accidental

0.81

 disruption

0.81

Activations Density 0.339%

phrases related to avoiding potential negative outcomes

phrases related to avoiding negative outcomes or risks

No Comments

No Known Activations