INDEX

Explanations

Chinese city names

oai_token-act-pair · gpt-3.5-turbo

references to specific locations and names of individuals involved in events or context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 sacrific

-0.74

brance

-0.66

 macros

-0.65

 administ

-0.65

ESSION

-0.63

 destro

-0.62

byter

-0.61

 COVER

-0.61

Pwr

-0.61

 burg

-0.61

POSITIVE LOGITS

hua

1.15

wei

1.13

jin

1.11

Tsu

1.10

yang

1.10

Bai

1.09

jri

1.07

Tai

1.07

ju

1.06

zhen

1.05

Activations Density 0.261%

Chinese city names

references to specific locations and names of individuals involved in events or context

No Comments

No Known Activations