INDEX

Explanations

terms related to the immune system and immune responses

oai_token-act-pair · gpt-3.5-turbo

references to the immune system and its interactions

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

 Nights

-0.78

 Franch

-0.76

é»Ĵ

-0.69

ãĥĺ

-0.69

faced

-0.68

udeb

-0.67

 Manziel

-0.65

Sund

-0.65

 Bans

-0.65

Winged

-0.65

POSITIVE LOGITS

 gland

1.13

otonin

1.10

 glands

1.02

 neurotrans

0.96

 reacting

0.91

 enzymes

0.90

 react

0.89

 stimulating

0.89

 enzyme

0.88

 serotonin

0.85

Activations Density 0.122%

terms related to the immune system and immune responses

references to the immune system and its interactions

No Comments

No Known Activations