INDEX

Explanations

quantities or measurements mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

words related to measurements and quantities of consumable items

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 architecture

-0.76

 incumb

-0.68

 invari

-0.68

avid

-0.64

 Ruins

-0.63

 arche

-0.62

stru

-0.62

 canonical

-0.62

 pioneer

-0.61

 backward

-0.60

POSITIVE LOGITS

 bottles

1.41

 bottle

1.28

 cans

1.14

 cigarettes

1.01

 whiskey

0.99

 vodka

0.97

 liquor

0.96

cig

0.95

 batches

0.93

 alcohol

0.91

Activations Density 0.253%

quantities or measurements mentioned in the text

words related to measurements and quantities of consumable items

No Comments

No Known Activations