INDEX

Explanations

proper nouns related to specific locations or events

oai_token-act-pair · gpt-3.5-turbo

names of locations or geographical places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

-0.97

vana

-0.78

ilater

-0.76

agonists

-0.74

orders

-0.73

ãĥĻ

-0.73

gypt

-0.73

atsuki

-0.72

aphael

-0.70

 seiz

-0.69

POSITIVE LOGITS

 County

1.46

 Township

1.39

 resident

1.22

 Borough

1.15

 Police

1.13

 Heights

1.11

 Mayor

1.11

shire

1.10

 Parish

1.08

 Beach

1.08

Activations Density 0.385%

proper nouns related to specific locations or events

names of locations or geographical places

No Comments

No Known Activations