INDEX

Explanations

references to spaces or locations

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

Head Attr Weights

0:0.07

1:0.09

2:0.09

3:0.07

4:0.07

5:0.09

6:0.07

7:0.09

8:0.08

9:0.08

10:0.08

11:0.09

Negative Logits

into

-1.68

 Fiat

-1.67

 mattress

-1.57

 accelerator

-1.45

wine

-1.41

Zy

-1.37

 onto

-1.36

 aloud

-1.35

stadt

-1.33

etc

-1.31

POSITIVE LOGITS

erest

1.73

 conflic

1.58

 Salmon

1.53

icer

1.51

quickShipAvailable

1.49

Orig

1.48

 Democr

1.47

luck

1.46

vic

1.45

 Conflict

1.44

Activations Density 0.000%

references to spaces or locations

No Known Activations