INDEX

Explanations

gratitude and acknowledgment expressions

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing the word "first" 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 @ 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

etheless

-1.00

cffff

-0.72

sung

-0.71

atten

-0.68

laugh

-0.68

nes

-0.68

sports

-0.68

owl

-0.66

cel

-0.65

far

-0.65

POSITIVE LOGITS

 introdu

1.03

asma

0.76

ODUCT

0.76

 assume

0.67

 introduction

0.67

 premise

0.65

 assumption

0.64

 Explain

0.64

 disclaimer

0.64

ASY

0.63

Activations Density 0.294%

gratitude and acknowledgment expressions

phrases emphasizing the word "first" in various contexts

No Comments

No Known Activations