INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.1.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

1:0.08

2:0.08

3:0.06

4:0.09

5:0.07

6:0.07

7:0.07

8:0.07

9:0.07

10:0.07

11:0.13

Negative Logits

 VIDEOS

-1.71

 flares

-1.66

』

-1.57

rats

-1.57

戦

-1.51

fest

-1.50

 Ryder

-1.50

 Conclusion

-1.49

!]

-1.48

 readings

-1.47

POSITIVE LOGITS

 administr

2.03

coh

1.83

 delegated

1.80

 Administ

1.79

 administ

1.78

 mathemat

1.78

iciary

1.75

 notor

1.73

administ

1.64

ublic

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.