INDEX

Explanations

phrases related to throwing or selling items at specific targets

oai_token-act-pair · gpt-3.5-turbo

prepositions and phrases indicating location or direction

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

jri

-0.65

iator

-0.65

wx

-0.64

PRESS

-0.62

Po

-0.60

izoph

-0.59

tri

-0.59

Rah

-0.59

Bo

-0.58

CRE

-0.58

POSITIVE LOGITS

pload

0.91

ãĥ¼ãĥ«

0.67

arettes

0.65

vertisements

0.64

 remotely

0.62

 Havana

0.61

izont

0.61

washer

0.60

bilt

0.58

 handheld

0.58

Activations Density 0.521%

phrases related to throwing or selling items at specific targets

prepositions and phrases indicating location or direction

No Comments

No Known Activations