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

1:0.06

2:0.08

3:0.09

4:0.09

5:0.08

6:0.08

7:0.07

8:0.09

9:0.07

10:0.06

11:0.08

Negative Logits

unic

-1.89

 crypt

-1.83

dit

-1.71

legged

-1.64

ilaterally

-1.60

 orgasm

-1.57

 elig

-1.52

inately

-1.52

tf

-1.51

crypt

-1.50

POSITIVE LOGITS

,''

1.68

ablishment

1.65

 forged

1.64

atures

1.57

 Koran

1.54

 concerted

1.51

SPONSORED

1.50

 batted

1.49

cknow

1.43

ctors

1.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.