INDEX

Explanations

mentions of improvement or comparison for different scenarios, with a preference towards the concept of "better"

oai_token-act-pair · gpt-3.5-turbo

the word "better" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Pione

-0.73

ategory

-0.66

cha

-0.65

sup

-0.64

ette

-0.63

cano

-0.62

amine

-0.61

kaya

-0.61

umo

-0.60

ums

-0.59

POSITIVE LOGITS

 than

1.31

than

1.09

 suited

1.08

 behaved

1.04

 Than

1.03

ment

0.95

 acquainted

0.94

 equipped

0.86

ments

0.81

 luck

0.80

Activations Density 0.067%

mentions of improvement or comparison for different scenarios, with a preference towards the concept of "better"

the word "better" and its variations

No Comments

No Known Activations