INDEX

Explanations

phrases related to the impact of actions or events on specific entities

oai_token-act-pair · gpt-3.5-turbo

phrases indicating effects or impacts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SourceFile

-0.87

aniel

-0.83

VPN

-0.75

lich

-0.74

BuyableInstoreAndOnline

-0.71

bug

-0.70

chool

-0.70

leground

-0.70

©¶æ¥µ

-0.69

LEY

-0.69

POSITIVE LOGITS

 morale

1.15

erous

1.09

 behalf

0.91

 profitability

0.87

 perceptions

0.85

 circulation

0.84

 interstate

0.81

 viability

0.81

 visibility

0.81

 perception

0.81

Activations Density 0.061%

phrases related to the impact of actions or events on specific entities

phrases indicating effects or impacts

No Comments

No Known Activations