INDEX

Explanations

political and economic references, particularly those related to leadership and electoral dynamics

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.02

1:0.02

2:0.03

3:0.04

4:0.07

5:0.52

6:0.02

7:0.03

8:0.02

9:0.12

10:0.02

11:0.03

Negative Logits

actly

-4.11

 exactly

-3.37

MpServer

-3.14

 Anyway

-3.11

brance

-3.10

,,,,,,,,

-3.07

Actually

-3.07

;;;;

-3.03

ynes

-3.02

ECA

-2.96

POSITIVE LOGITS

 unfolds

4.90

 prepares

4.79

 grows

4.67

 progresses

4.42

 fades

4.29

 evolves

4.22

 continues

4.21

 emerges

4.07

 expands

4.04

 progressed

4.02

Activations Density 0.318%

political and economic references, particularly those related to leadership and electoral dynamics

No Known Activations