INDEX

Explanations

references to United States senators

oai_token-act-pair · gpt-3.5-turbo

references to U.S. Senators

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zb

-0.78

zsche

-0.76

 traffickers

-0.72

pecially

-0.71

hiba

-0.70

 underpin

-0.69

obyl

-0.68

 scoop

-0.67

 cradle

-0.67

ebook

-0.66

POSITIVE LOGITS

 Barack

0.94

 Dianne

0.93

 Patrick

0.93

 Olympia

0.93

 John

0.91

 Lamar

0.90

 Jesse

0.90

 Majority

0.89

 Scott

0.88

 Mike

0.88

Activations Density 0.032%

references to United States senators

references to U.S. Senators

No Comments

No Known Activations