INDEX

Explanations

interjections and casual affirmations

oai_token-act-pair · gpt-3.5-turbo

expressions of agreement or acknowledgment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 fullest

-0.74

igmat

-0.70

 appreciated

-0.69

 currencies

-0.68

 burd

-0.67

multipl

-0.67

wives

-0.59

¿

-0.59

 concert

-0.59

 throats

-0.58

POSITIVE LOGITS

ipop

0.94

 Nope

0.91

oil

0.81

Huh

0.79

Yep

0.77

imedia

0.77

wl

0.76

yssey

0.74

swick

0.73

edia

0.73

Activations Density 0.018%

interjections and casual affirmations

expressions of agreement or acknowledgment

No Comments

No Known Activations