INDEX

Explanations

references to physical gates or barriers

oai_token-act-pair · gpt-3.5-turbo

references to gates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ortium

-0.89

enegger

-0.77

 Hots

-0.77

lihood

-0.68

inho

-0.67

ocker

-0.64

 Norm

-0.60

aceous

-0.59

ucket

-0.59

 narrated

-0.59

POSITIVE LOGITS

keepers

1.30

keeper

1.25

 gates

1.16

 gate

1.16

ways

1.01

stones

1.01

posts

0.96

holes

0.93

hole

0.92

house

0.90

Activations Density 0.005%

references to physical gates or barriers

references to gates

No Comments

No Known Activations