INDEX

Explanations

occurrences of the word "Joe"

oai_token-act-pair · gpt-3.5-turbo

the presence of the substring "oe" in words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ifiers

-0.84

ifiable

-0.81

ifier

-0.79

 Ambro

-0.70

ifications

-0.69

abad

-0.69

 glim

-0.68

ivities

-0.67

arians

-0.67

rons

-0.66

POSITIVE LOGITS

ppel

1.23

zie

1.10

zzi

1.05

lect

1.03

cean

1.02

hler

1.01

hner

0.97

hl

0.95

utenant

0.94

ffer

0.94

Activations Density 0.018%

occurrences of the word "Joe"

the presence of the substring "oe" in words

No Comments

No Known Activations