INDEX

Explanations

mentions of verification or affirmation

oai_token-act-pair · gpt-3.5-turbo

the word "indeed" in various contexts indicating affirmation or confirmation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

epend

-0.55

Base

-0.55

Active

-0.52

ele

-0.51

bee

-0.51

Args

-0.51

Kid

-0.50

 System

-0.50

isle

-0.50

 Montana

-0.50

POSITIVE LOGITS

 indeed

4.03

 moreover

1.50

Indeed

1.41

 certainly

1.37

 doubtless

1.37

 Indeed

1.35

 furthermore

1.34

 undoubtedly

1.25

 surely

1.21

 consequently

1.17

Activations Density 0.018%

mentions of verification or affirmation

the word "indeed" in various contexts indicating affirmation or confirmation

No Comments

No Known Activations