INDEX

Explanations

references to iconic cultural symbols or figures in various contexts

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

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

Not in Any Lists

No Comments

Head Attr Weights

0:0.12

1:0.31

2:0.06

3:0.07

4:0.03

5:0.02

6:0.04

7:0.10

8:0.01

9:0.03

10:0.13

11:0.03

Negative Logits

 strugg

-2.78

 horizont

-2.61

 Cumm

-2.56

Background

-2.55

 Borders

-2.54

iffe

-2.49

abase

-2.49

riel

-2.48

 Takeru

-2.45

 Cros

-2.42

POSITIVE LOGITS

 Golden

8.47

Golden

7.87

 golden

6.14

gold

5.17

 GOLD

4.29

 Gold

3.90

 gold

3.81

Gold

3.73

 Warriors

3.49

 Marin

3.48

Activations Density 0.023%

references to iconic cultural symbols or figures in various contexts

No Comments

No Known Activations