INDEX

Explanations

numeric entities, specifically ordinal numbers indicating sequence or ranking

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate the first occurrence of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

body

-0.67

terday

-0.65

bach

-0.61

æ³

-0.59

inem

-0.59

=-=-=-=-=-=-=-=-

-0.56

uction

-0.56

ble

-0.56

FW

-0.56

hya

-0.55

POSITIVE LOGITS

sever

0.85

 many

0.74

many

0.74

 three

0.74

two

0.71

 several

0.70

 innumerable

0.68

urst

0.68

uits

0.68

 four

0.67

Activations Density 0.098%

numeric entities, specifically ordinal numbers indicating sequence or ranking

phrases that indicate the first occurrence of something

No Comments

No Known Activations