INDEX

Explanations

terms related to personal preferences or inclinations towards something

oai_token-act-pair · gpt-3.5-turbo

words related to favoritism or preference

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hook

-0.71

meal

-0.68

 Tanner

-0.65

Hour

-0.65

 Operator

-0.64

 Declaration

-0.64

quartered

-0.64

FORMATION

-0.63

wreck

-0.62

THER

-0.62

POSITIVE LOGITS

Fav

1.29

fav

1.22

itism

1.05

ours

0.93

iants

0.82

oured

0.80

ouri

0.79

ited

0.78

iors

0.77

ilial

0.77

Activations Density 0.004%

terms related to personal preferences or inclinations towards something

words related to favoritism or preference

No Comments

No Known Activations