INDEX

Explanations

factual information and technical details

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

strong positive sentiments about experiences or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-att-kk

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.04

1:0.30

2:0.06

3:0.02

4:0.06

5:0.11

6:0.07

7:0.05

8:0.05

9:0.05

10:0.07

11:0.06

Negative Logits

etheless

-2.35

wcs

-1.96

��

-1.84

DragonMagazine

-1.78

 neighb

-1.65

 lapt

-1.63

 periodic

-1.59

 satell

-1.59

abwe

-1.59

 submar

-1.58

POSITIVE LOGITS

Said

1.86

":"","

1.67

ヴ

1.61

 Said

1.60

 "...

1.56

Nou

1.53

 quotes

1.53

 Says

1.43

 Seconds

1.43

":[

1.42

Activations Density 0.107%

factual information and technical details

strong positive sentiments about experiences or events

No Comments

No Known Activations