INDEX

Explanations

references to physical objects used for drinking, such as mugs

oai_token-act-pair · gpt-3.5-turbo

references to physical objects like mugs and jugs, particularly in a contextual or metaphorical sense

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

×Ļ×

-0.75

cision

-0.67

edient

-0.66

hovah

-0.65

IGH

-0.63

secondary

-0.63

ipher

-0.63

 Virgin

-0.63

judicial

-0.62

thodox

-0.62

POSITIVE LOGITS

mug

1.32

gers

1.00

shots

0.93

ging

0.90

atures

0.90

Mug

0.88

shot

0.84

ger

0.83

ged

0.80

ograph

0.79

Activations Density 0.007%

references to physical objects used for drinking, such as mugs

references to physical objects like mugs and jugs, particularly in a contextual or metaphorical sense

No Comments

No Known Activations