INDEX

Explanations

words related to legal entities or individuals' names

oai_token-act-pair · gpt-3.5-turbo

mentions of a specific individual named "Card" or variations of the name

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

¿½

-1.02

hower

-0.79

Ń·

-0.73

ĸļ

-0.73

merce

-0.72

á½

-0.71

ithing

-0.70

%]

-0.67

 Siem

-0.66

akings

-0.65

POSITIVE LOGITS

iovascular

1.38

inals

1.23

iologist

1.15

iac

1.15

ozo

1.10

assian

1.06

igans

1.01

iov

1.00

board

1.00

igan

0.99

Activations Density 0.018%

words related to legal entities or individuals' names

mentions of a specific individual named "Card" or variations of the name

No Comments

No Known Activations