INDEX

Explanations

references to achievements or victories

oai_token-act-pair · gpt-3.5-turbo

entities related to competitive events and awards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

amber

-0.77

 Barney

-0.74

annels

-0.73

 cables

-0.72

 Cable

-0.72

 Hicks

-0.70

 Rept

-0.70

IRC

-0.70

 Antar

-0.70

mask

-0.69

POSITIVE LOGITS

win

2.18

Win

2.07

Win

2.05

win

2.03

 wins

1.95

 Winning

1.92

 winning

1.88

WIN

1.88

WIN

1.72

 victory

1.70

Activations Density 0.218%

references to achievements or victories

entities related to competitive events and awards

No Comments

No Known Activations