INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

1:0.09

2:0.08

3:0.07

4:0.07

5:0.07

6:0.08

7:0.06

8:0.08

9:0.08

10:0.08

11:0.09

Negative Logits

tro

-1.96

apore

-1.66

cele

-1.44

 dragons

-1.43

lde

-1.42

cho

-1.41

oration

-1.38

 Hera

-1.37

cheat

-1.36

wagen

-1.36

POSITIVE LOGITS

ONSORED

2.25

OCK

1.68

+++

1.65

 Oliv

1.54

GGGGGGGG

1.54

++++++++++++++++

1.51

 Ramirez

1.46

 Gutierrez

1.46

ertodd

1.45

Rid

1.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.