INDEX

Explanations

mentions and references to the Dalai Lama

oai_token-act-pair · gpt-3.5-turbo

mentions of the Dalai Lama

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

sburgh

-0.78

ramid

-0.78

edia

-0.77

Myr

-0.73

afort

-0.69

heric

-0.68

nesota

-0.68

iak

-0.67

ded

-0.66

apor

-0.65

POSITIVE LOGITS

 Lama

1.06

 Dalai

0.98

ç·

0.78

ãĤ¶

0.76

terness

0.75

etooth

0.74

ãĥ´

0.71

ª

0.70

 pengu

0.69

 pacif

0.69

Activations Density 0.015%

mentions and references to the Dalai Lama

mentions of the Dalai Lama

No Comments

No Known Activations