INDEX

Explanations

No Explanations Found

New Auto-Interp

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

0:0.08

1:0.10

2:0.08

3:0.07

4:0.08

5:0.09

6:0.07

7:0.07

8:0.07

9:0.07

10:0.08

11:0.07

Negative Logits

cheon

-2.16

 Upton

-1.79

TBA

-1.67

 Spotlight

-1.62

 Maxwell

-1.59

 Marriott

-1.58

Lia

-1.58

 Watt

-1.49

 included

-1.49

 Sierra

-1.48

POSITIVE LOGITS

javascript

1.63

1.58

gradient

1.51

angles

1.49

onential

1.49

ihad

1.46

 warriors

1.46

 apocalyptic

1.45

ocobo

1.44

 encount

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.