INDEX

Explanations

references to unsafe or unhealthy conditions and behaviors

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

words related to unhealthy and unsafe conditions or behavior

oai_token-act-pair · gpt-3.5-turbo

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

soType

-0.99

glas

-0.92

tsky

-0.88

ophers

-0.83

sheets

-0.83

veland

-0.82

agra

-0.81

phrase

-0.80

DragonMagazine

-0.79

vironment

-0.79

POSITIVE LOGITS

 undermin

0.73

 wastes

0.73

 compromises

0.73

 unreasonable

0.71

ities

0.70

 Ukrain

0.70

 duplication

0.69

 disproportion

0.68

 behaviour

0.67

 tendencies

0.66

Activations Density 0.040%

references to unsafe or unhealthy conditions and behaviors

words related to unhealthy and unsafe conditions or behavior

No Comments

No Known Activations