INDEX

Explanations

proper nouns, potentially related to celebrities or individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns or names associated with specific individuals or entities

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

 Reincarn

-0.77

 Leban

-0.75

 conclud

-0.70

merce

-0.67

perty

-0.66

ĨĴ

-0.65

CLASSIFIED

-0.63

 INCLUD

-0.63

hovah

-0.63

 retaliation

-0.61

POSITIVE LOGITS

ibrary

0.93

gow

0.83

heed

0.81

udic

0.80

iberal

0.78

tarians

0.70

uce

0.70

ounge

0.68

ï¸ı

0.66

ansk

0.65

Activations Density 0.771%

proper nouns, potentially related to celebrities or individuals

proper nouns or names associated with specific individuals or entities

No Comments

No Known Activations