INDEX

Explanations

proper nouns related to a specific name "Tan"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Tan" and variations of the word "tan."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ãĤ¡

-0.90

Ö¼

-0.80

ģĸ

-0.71

 Madison

-0.69

llor

-0.69

vous

-0.69

çīĪ

-0.67

ngth

-0.67

OUS

-0.66

 GDDR

-0.66

POSITIVE LOGITS

nery

1.22

geon

1.11

ning

1.09

zan

1.01

jug

0.94

emark

0.90

uki

0.89

oco

0.89

elope

0.86

aka

0.86

Activations Density 0.019%

proper nouns related to a specific name "Tan"

mentions of the name "Tan" and variations of the word "tan."

No Comments

No Known Activations