INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

3:0.09

4:0.07

5:0.07

6:0.09

7:0.09

8:0.08

9:0.07

10:0.08

11:0.07

Negative Logits

Bloom

-3.10

Alert

-2.69

Rog

-2.59

Rogue

-2.50

Weak

-2.49

 toxin

-2.48

ribly

-2.46

noxious

-2.45

isd

-2.42

 Toxic

-2.40

POSITIVE LOGITS

"],"

2.80

 Stras

2.78

 pave

2.75

 Cardinals

2.64

 arrang

2.63

�

2.60

 Zionism

2.49

 Pont

2.47

 somew

2.43

 Palest

2.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.