INDEX

Explanations

phrases related to political events and names

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

gerunds or present participles ending in 'ing'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-att-kk

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.08

1:0.09

2:0.08

3:0.07

4:0.08

5:0.06

6:0.09

7:0.08

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

gotten

-1.36

folk

-1.34

plom

-1.32

 democracy

-1.31

 concentrated

-1.25

 Prelude

-1.23

orage

-1.23

.--

-1.22

 calculus

-1.21

heric

-1.20

POSITIVE LOGITS

��

1.79

�

1.73

��

1.73

��

1.72

═

1.70

版

1.66

ل

1.62

��

1.60

ْ

1.59

IAS

1.59

Activations Density 0.000%

phrases related to political events and names

gerunds or present participles ending in 'ing'

No Comments

No Known Activations