INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.09

1:0.08

2:0.08

3:0.07

4:0.07

5:0.07

6:0.07

7:0.08

8:0.09

9:0.08

10:0.09

11:0.07

Negative Logits

soDeliveryDate

-1.84

taboola

-1.74

forums

-1.72

issan

-1.64

 livest

-1.58

ibaba

-1.56

cellence

-1.56

Weather

-1.53

nutrition

-1.52

ribune

-1.52

POSITIVE LOGITS

 intervening

1.79

 Expend

1.61

itri

1.60

?'"

1.52

 shove

1.49

 forc

1.49

 GOODMAN

1.48

 Appropri

1.47

 insertion

1.45

ロ

1.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.