INDEX

Explanations

instances of the word "it", with varying degrees of emphasis

oai_token-act-pair · gpt-3.5-turbo

the pronoun "it" used in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Polk

-0.67

peed

-0.67

Magikarp

-0.60

Gul

-0.60

TJ

-0.59

FUL

-0.59

GROUND

-0.56

dden

-0.55

Management

-0.55

 Patton

-0.55

POSITIVE LOGITS

 belongs

1.42

 reflects

1.39

 relates

1.37

 contains

1.36

 involves

1.36

 represents

1.34

 resembles

1.34

 differs

1.32

 applies

1.32

 encompasses

1.31

Activations Density 0.273%

instances of the word "it", with varying degrees of emphasis

the pronoun "it" used in various contexts

No Comments

No Known Activations