INDEX

Explanations

phrases related to legal and investigative actions

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 whilst

-0.92

 ðŁĻĤ

-0.77

!".

-0.77

 haha

-0.75

 fuck

-0.72

 civilisation

-0.71

".[

-0.71

Fuck

-0.70

Âł

-0.70

 util

-0.69

POSITIVE LOGITS

 Grassley

0.87

 spokeswoman

0.83

 POLITICO

0.82

 McDonnell

0.82

 Oversight

0.81

 Rodham

0.78

 Arlington

0.77

 spokesman

0.77

 Corker

0.77

 Anchorage

0.75

Activations Density 1.608%

phrases related to legal and investigative actions

No Comments

No Known Activations