INDEX

Explanations

phrases related to causing harm or damage

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate harm or damage to entities or systems

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

DragonMagazine

-0.72

soDeliveryDate

-0.69

iguous

-0.66

 Edited

-0.66

wine

-0.65

lich

-0.63

reflect

-0.63

atonin

-0.62

fw

-0.62

isson

-0.62

POSITIVE LOGITS

 entire

1.09

 livelihood

0.99

 credibility

0.97

 sensibilities

0.88

 incumb

0.85

 reputation

0.85

 whole

0.85

 effectiveness

0.83

 morale

0.83

 psyche

0.83

Activations Density 0.307%

phrases related to causing harm or damage

phrases that indicate harm or damage to entities or systems

No Comments

No Known Activations