INDEX

Explanations

terms related to sensitivity, especially in the context of various studies and scenarios

oai_token-act-pair · gpt-3.5-turbo

instances of the word "sensitivity" in various contexts

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

ghazi

-0.80

raine

-0.70

areth

-0.67

corn

-0.67

thus

-0.67

doc

-0.66

 Camel

-0.65

eu

-0.65

riage

-0.65

iverse

-0.64

POSITIVE LOGITS

 sensitivity

1.03

ivities

0.96

ensitivity

0.85

 sensit

0.82

 Flavoring

0.78

 tolerant

0.78

ibility

0.76

xual

0.74

é¾įå¥ĳå£«

0.74

 sensitive

0.73

Activations Density 0.026%

terms related to sensitivity, especially in the context of various studies and scenarios

instances of the word "sensitivity" in various contexts

No Comments

No Known Activations