INDEX

Explanations

titles or phrases denoted by certain symbols

oai_token-act-pair · gpt-3.5-turbo

titled sections and documents with specific references or headings

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

 range

-0.80

 detached

-0.73

 sear

-0.73

 shroud

-0.73

 leap

-0.73

 destro

-0.72

creen

-0.72

 grips

-0.68

 fragmentation

-0.67

 scramble

-0.66

POSITIVE LOGITS

ª

1.14

ł

1.14

ı

1.05

¹

1.03

ĳ

0.99

Ĵ

0.98

Quantity

0.95

¡

0.92

Vers

0.91

½

0.90

Activations Density 0.162%

titles or phrases denoted by certain symbols

titled sections and documents with specific references or headings

No Comments

No Known Activations