INDEX

Explanations

terms related to bottled water or canned food products

oai_token-act-pair · gpt-3.5-turbo

references to bottled and canned food products

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nesota

-0.91

lihood

-0.88

rn

-0.85

xual

-0.79

ffield

-0.78

igel

-0.76

eds

-0.75

eston

-0.74

hov

-0.73

lde

-0.72

POSITIVE LOGITS

 bottled

1.03

 peanuts

0.76

 liquor

0.74

 beverages

0.73

 groundwater

0.72

 beverage

0.71

 containers

0.70

 water

0.69

BALL

0.68

ModLoader

0.68

Activations Density 0.019%

terms related to bottled water or canned food products

references to bottled and canned food products

No Comments

No Known Activations