INDEX

Explanations

phrases related to physical struggle or conflict

oai_token-act-pair · gpt-3.5-turbo

instances of the word "str" and related forms, suggesting a focus on words indicating strength or structural elements

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

peat

-0.74

shots

-0.74

pei

-0.73

jay

-0.72

boys

-0.70

manship

-0.67

¥µ

-0.67

hyde

-0.66

bear

-0.66

hide

-0.65

POSITIVE LOGITS

ategy

1.25

ained

1.25

ainer

1.19

ategic

1.16

aining

1.11

uments

1.03

icken

1.03

anded

1.01

aints

0.99

angled

0.98

Activations Density 0.013%

phrases related to physical struggle or conflict

instances of the word "str" and related forms, suggesting a focus on words indicating strength or structural elements

No Comments

No Known Activations