INDEX

Explanations

letters 'N' followed by a number

oai_token-act-pair · gpt-3.5-turbo

references to the letter 'N' in various contexts

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

 Gibraltar

-0.68

Vaj

-0.67

 Cerberus

-0.66

 diplom

-0.65

 Sparrow

-0.65

 communism

-0.64

espie

-0.64

 unsupported

-0.64

 surve

-0.63

 Izan

-0.62

POSITIVE LOGITS

onsense

1.24

ucle

1.24

aughty

1.20

anny

1.16

usra

1.15

ihil

1.13

ectar

1.10

umeric

1.09

ipple

1.08

umerous

1.08

Activations Density 0.040%

letters 'N' followed by a number

references to the letter 'N' in various contexts

No Comments

No Known Activations