INDEX

Explanations

phrases or sentences involving visual descriptions of people's actions

oai_token-act-pair · gpt-3.5-turbo

repetitive phrases containing the word "in."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

etheless

-0.74

cia

-0.73

idays

-0.68

matically

-0.68

 Secondly

-0.66

,...

-0.62

!:

-0.61

rolet

-0.61

ystem

-0.61

Ħ¢

-0.61

POSITIVE LOGITS

 unison

1.44

 disbelief

1.33

 agony

1.25

 frustration

1.25

 amaz

1.24

awe

1.21

 anguish

1.19

 vain

1.18

 admiration

1.18

 anticipation

1.18

Activations Density 0.130%

phrases or sentences involving visual descriptions of people's actions

repetitive phrases containing the word "in."

No Comments

No Known Activations