INDEX

Explanations

ATM-related terms or references in text

oai_token-act-pair · gpt-3.5-turbo

references to Automated Teller Machines (ATMs)

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

hov

-0.73

hua

-0.72

SOURCE

-0.72

Quality

-0.71

ãĤ¡

-0.71

published

-0.70

Ham

-0.69

 Hodg

-0.69

mary

-0.68

POSITIVE LOGITS

ATM

1.06

 withdrawals

1.01

igmatic

0.88

elaide

0.88

abase

0.86

 suspic

0.83

ega

0.82

ntil

0.82

EGA

0.80

jriwal

0.80

Activations Density 0.005%

ATM-related terms or references in text

references to Automated Teller Machines (ATMs)

No Comments

No Known Activations