INDEX

Explanations

phrases related to ranking and comparison, particularly in terms of excellence

oai_token-act-pair · gpt-3.5-turbo

phrases related to ranked competitions and performance metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ĸļ

-0.97

actionDate

-0.74

 guiActiveUn

-0.70

UGE

-0.66

pora

-0.65

jit

-0.64

sv

-0.63

Topics

-0.63

NetMessage

-0.62

utory

-0.60

POSITIVE LOGITS

 EVER

0.75

tein

0.73

 outcomes

0.72

 imaginable

0.71

 Worst

0.68

achev

0.68

iev

0.66

 Ever

0.65

 behaved

0.64

seller

0.63

Activations Density 0.178%

phrases related to ranking and comparison, particularly in terms of excellence

phrases related to ranked competitions and performance metrics

No Comments

No Known Activations