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

0:0.09

1:0.07

2:0.08

3:0.09

4:0.09

5:0.08

6:0.08

7:0.07

8:0.06

9:0.07

10:0.08

11:0.09

Negative Logits

Reviewer

-1.81

ウス

-1.67

raltar

-1.60

idel

-1.58

itud

-1.44

atu

-1.36

ß

-1.35

COMPLE

-1.34

アル

-1.33

 synt

-1.33

POSITIVE LOGITS

 CNBC

1.48

 exaggeration

1.45

 NEWS

1.37

 Whip

1.34

 tweeting

1.28

 skew

1.28

Deg

1.27

 Journalists

1.27

 Coffin

1.26

 viewership

1.26

Activations Density 0.000%

No Known Activations

This feature has no known activations.