INDEX

Explanations

phrases describing something as straightforward or uncomplicated

oai_token-act-pair · gpt-3.5-turbo

references to simplicity 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arians

-0.80

mouth

-0.75

 Awards

-0.72

auer

-0.67

 Meanwhile

-0.64

buster

-0.63

âĹ¼

-0.63

icipated

-0.62

ree

-0.62

wake

-0.62

POSITIVE LOGITS

 simple

3.35

simple

2.73

 Simple

2.26

Simple

2.07

 straightforward

2.05

 simpler

2.03

 simplest

1.99

 simplistic

1.85

 simplicity

1.74

 easy

1.63

Activations Density 0.023%

phrases describing something as straightforward or uncomplicated

references to simplicity in various contexts

No Comments

No Known Activations