INDEX

Explanations

phrases or topics related to size or scale

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "larger" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Exile

-0.77

elf

-0.73

ocracy

-0.73

eline

-0.72

onso

-0.70

 Bleach

-0.70

ILLE

-0.69

 Called

-0.68

SR

-0.67

Yel

-0.67

POSITIVE LOGITS

 sized

1.15

 intestine

1.02

 than

0.96

than

0.95

 eleph

0.95

 quantities

0.94

 diameter

0.84

 scale

0.80

 proport

0.80

 carniv

0.79

Activations Density 0.012%

phrases or topics related to size or scale

references to the concept of "larger" in various contexts

No Comments

No Known Activations