INDEX

Explanations

answers or responses to questions

oai_token-act-pair · gpt-3.5-turbo

phrases that involve answering questions or providing responses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

acent

-0.72

ixie

-0.64

raint

-0.63

atin

-0.63

oult

-0.61

uren

-0.61

enta

-0.60

paces

-0.60

eder

-0.59

lite

-0.58

POSITIVE LOGITS

 questions

1.80

 question

1.64

 queries

1.38

 Questions

1.35

 QUEST

1.34

 dilemma

1.30

Question

1.26

question

1.23

 inquiries

1.23

 dile

1.22

Activations Density 0.879%

answers or responses to questions

phrases that involve answering questions or providing responses

No Comments

No Known Activations