INDEX

Explanations

proper nouns, likely names or brands

oai_token-act-pair · gpt-3.5-turbo

variations of the word "viva."

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

*/(

-0.73

mart

-0.69

 incumbent

-0.69

quartered

-0.67

onymous

-0.66

later

-0.66

frames

-0.66

piece

-0.64

 setbacks

-0.64

ocalyptic

-0.63

POSITIVE LOGITS

iva

1.11

ivas

0.91

ahu

0.81

arov

0.81

BILITY

0.81

asa

0.80

ISION

0.78

enza

0.78

ishi

0.78

Rao

0.78

Activations Density 0.023%

proper nouns, likely names or brands

variations of the word "viva."

No Comments

No Known Activations