INDEX

Explanations

phrases related to safety and security

oai_token-act-pair · gpt-3.5-turbo

references to safety and secure environments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

issance

-0.91

naire

-0.79

yss

-0.77

fred

-0.67

 elig

-0.66

onde

-0.63

 Revenue

-0.62

ional

-0.61

pain

-0.61

hedral

-0.60

POSITIVE LOGITS

 havens

0.97

inventoryQuantity

0.93

keeping

0.90

haven

0.85

 harbor

0.80

 bets

0.78

 haven

0.76

 Haven

0.74

 isot

0.74

 deposit

0.73

Activations Density 0.033%

phrases related to safety and security

references to safety and secure environments

No Comments

No Known Activations