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

0:0.07

1:0.07

2:0.08

3:0.07

4:0.08

5:0.08

6:0.08

7:0.06

8:0.09

9:0.09

10:0.09

11:0.07

Negative Logits

ylum

-1.35

redd

-1.23

 ransom

-1.20

emort

-1.18

ideo

-1.18

render

-1.15

 objective

-1.15

tro

-1.14

Pref

-1.13

Redd

-1.13

POSITIVE LOGITS

endi

1.47

 Antar

1.42

igne

1.39

yog

1.36

]."

1.35

 tallest

1.34

lance

1.33

 Tant

1.33

INESS

1.31

��

1.31

Activations Density 0.000%

No Known Activations

This feature has no known activations.