INDEX

Explanations

questions introduced by the word "Which"

oai_token-act-pair · gpt-3.5-turbo

questions starting with "Which."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

gy

-0.74

burg

-0.67

athi

-0.66

rollers

-0.65

mage

-0.65

pat

-0.65

Gy

-0.64

bed

-0.64

bd

-0.64

rene

-0.64

POSITIVE LOGITS

soever

1.30

ãĥ¯ãĥ³

0.82

 begs

0.79

xual

0.79

 convol

0.77

 brings

0.76

ãĥ¼ãĥĨãĤ£

0.74

 happ

0.70

ync

0.67

espie

0.67

Activations Density 0.013%

questions introduced by the word "Which"

questions starting with "Which."

No Comments

No Known Activations