INDEX

Explanations

locations and landmarks

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of places and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

¦

-0.74

VALUE

-0.73

requ

-0.72

akable

-0.71

ãĥĻ

-0.71

arov

-0.70

ī

-0.69

agonists

-0.68

 destro

-0.67

 sacrific

-0.67

POSITIVE LOGITS

 County

1.34

 Borough

1.26

 Township

1.20

 Hills

1.11

 Heights

1.10

 resident

1.10

 Peninsula

1.10

 Valley

1.09

 Avenue

1.08

 residents

1.07

Activations Density 0.483%

locations and landmarks

proper nouns, specifically names of places and entities

No Comments

No Known Activations