INDEX

Explanations

phrases related to opening or unlocking something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "open" and its variations, often in contexts related to perception or opportunities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

SN

-0.67

utan

-0.67

jad

-0.65

esson

-0.63

axe

-0.61

lav

-0.59

 ducks

-0.57

 acqu

-0.56

kov

-0.56

chem

-0.56

POSITIVE LOGITS

 doors

1.06

 Pandora

1.05

izons

0.90

 door

0.86

 Doors

0.85

 gates

0.83

 portals

0.81

 rift

0.80

 throttle

0.76

 valves

0.76

Activations Density 0.095%

phrases related to opening or unlocking something

instances of the word "open" and its variations, often in contexts related to perception or opportunities

No Comments

No Known Activations