INDEX

Explanations

mentions of clothing items, particularly shirts

oai_token-act-pair · gpt-3.5-turbo

references to shirts and clothing-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 ingred

-0.67

sys

-0.64

ths

-0.64

 fert

-0.64

 prey

-0.63

SPONSORED

-0.63

 satellites

-0.62

 subsequ

-0.60

elsen

-0.59

nesota

-0.59

POSITIVE LOGITS

 sleeve

1.26

shirt

1.21

 sleeves

1.21

leeve

1.17

hirt

1.17

 shirts

1.13

 shirt

1.10

shirts

1.04

 Shirt

1.03

 collar

1.02

Activations Density 0.046%

mentions of clothing items, particularly shirts

references to shirts and clothing-related terms

No Comments

No Known Activations