INDEX

Explanations

words containing the substring "app" with varying intensities

oai_token-act-pair · gpt-3.5-turbo

the word "app" in various forms or contexts

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

EStreamFrame

-0.77

Îº

-0.67

 caution

-0.67

 guiActiveUn

-0.66

 sidx

-0.65

 formal

-0.63

trl

-0.63

maj

-0.62

 knot

-0.61

 sqor

-0.61

POSITIVE LOGITS

earance

1.56

ears

1.35

ointment

1.33

alach

1.27

earances

1.27

lied

1.25

eared

1.24

arently

1.22

arent

1.12

earing

1.07

Activations Density 0.011%

words containing the substring "app" with varying intensities

the word "app" in various forms or contexts

No Comments

No Known Activations