INDEX

Explanations

phrases related to the concept of passage of time and progression

oai_token-act-pair · gpt-3.5-turbo

Triggered by @bot

documents that contain frequent references to time-related phrases and sequences

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

Head Attr Weights

0:0.01

1:0.02

2:0.12

3:0.22

4:0.01

5:0.02

6:0.06

7:0.06

8:0.10

9:0.06

10:0.08

11:0.17

Negative Logits

Sov

-1.10

Nob

-1.10

olor

-1.08

RAW

-1.02

tle

-0.99

 srfAttach

-0.99

rets

-0.98

®

-0.97

 Pharma

-0.97

VK

-0.97

POSITIVE LOGITS

]}

1.31

 batter

1.28

anchester

1.15

ascus

1.12

 hoop

1.07

 vicinity

1.03

 fray

1.02

gypt

1.01

 corridors

0.99

phia

0.98

Activations Density 0.013%

phrases related to the concept of passage of time and progression

documents that contain frequent references to time-related phrases and sequences

No Known Activations