INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.03

1:0.01

2:0.08

3:0.14

4:0.07

5:0.02

6:0.08

7:0.11

8:0.07

9:0.04

10:0.17

11:0.12

Negative Logits

named

-1.57

artisan

-1.49

Ranked

-1.47

netflix

-1.45

dated

-1.42

龍契士

-1.41

conservancy

-1.40

 Firstly

-1.36

expected

-1.35

calling

-1.35

POSITIVE LOGITS

 embed

1.73

 approximation

1.62

 IMAGES

1.58

 attribution

1.57

 endif

1.56

Photos

1.53

 link

1.52

});

1.42

inkle

1.40

 retract

1.36

Activations Density 0.000%

No Known Activations

This feature has no known activations.