INDEX

Explanations

terms related to compassion

oai_token-act-pair · gpt-3.5-turbo

references to compassion and its related concepts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

kj

-0.75

jong

-0.72

 Rite

-0.70

*/(

-0.69

Bam

-0.68

wagen

-0.67

azeera

-0.65

andals

-0.65

bris

-0.64

ORN

-0.62

POSITIVE LOGITS

ately

0.89

 compassionate

0.86

 laureate

0.84

itably

0.81

 towards

0.79

ãĥĨãĤ£

0.77

 toward

0.76

 compassion

0.72

 Towards

0.72

giving

0.70

Activations Density 0.049%

terms related to compassion

references to compassion and its related concepts

No Comments

No Known Activations