INDEX

Explanations

personal names

oai_token-act-pair · gpt-3.5-turbo

mentions of names and proper nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

•EggList

No Comments

Negative Logits

 bleach

-0.85

 Bleach

-0.73

¡

-0.73

-0.72

idth

-0.67

Ble

-0.64

 Beckham

-0.64

 Chevron

-0.64

ected

-0.64

OUP

-0.63

POSITIVE LOGITS

1.41

1.25

mic

1.13

MI

1.10

mt

1.10

mill

1.08

mob

1.07

MN

1.06

mo

1.06

Ms

1.05

Activations Density 0.276%

personal names

mentions of names and proper nouns

No Comments

No Known Activations