INDEX

Explanations

mentions of specific terms such as "Esper," "broom," and "Hyde."

oai_token-act-pair · gpt-3.5-turbo

specific terms related to gaming and technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

hiba

-0.71

adeon

-0.70

akening

-0.70

ighting

-0.68

 tiss

-0.67

jad

-0.66

uron

-0.66

engineering

-0.64

imming

-0.64

¶æ

-0.63

POSITIVE LOGITS

anza

0.85

ENSE

0.78

lihood

0.74

ãĥ¼ãĥ«

0.74

knife

0.73

ENCE

0.73

BuyableInstoreAndOnline

0.71

 Garfield

0.71

anto

0.68

NER

0.67

Activations Density 0.017%

mentions of specific terms such as "Esper," "broom," and "Hyde."

specific terms related to gaming and technology

No Comments

No Known Activations