INDEX

Explanations

phrases starting with "Its" followed by a positive or negative statement

oai_token-act-pair · gpt-3.5-turbo

the word "its" and its variations, indicating descriptions or references to possession or condition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

--+

-0.74

VS

-0.68

 Thib

-0.67

iatus

-0.65

Ã¯

-0.65

ievers

-0.64

Obj

-0.64

GB

-0.63

":[

-0.62

imedia

-0.61

POSITIVE LOGITS

ELF

1.12

 gonna

0.93

 predecessor

0.90

 worth

0.88

 been

0.87

 supposed

0.85

own

0.85

elf

0.83

omorph

0.82

been

0.82

Activations Density 0.097%

phrases starting with "Its" followed by a positive or negative statement

the word "its" and its variations, indicating descriptions or references to possession or condition

No Comments

No Known Activations