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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.09

3:0.08

4:0.09

5:0.09

6:0.06

7:0.07

8:0.08

9:0.08

10:0.07

11:0.09

Negative Logits

issions

-1.64

igue

-1.60

][

-1.55

iciency

-1.51

vae

-1.50

hea

-1.43

 Tycoon

-1.43

itte

-1.40

ogenesis

-1.39

emp

-1.39

POSITIVE LOGITS

quickShipAvailable

1.59

DERR

1.51

 haircut

1.33

 traged

1.31

Assad

1.24

dan

1.24

 Tant

1.23

 vehement

1.22

 Butt

1.21

utterstock

1.20

Activations Density 0.000%

No Known Activations

This feature has no known activations.