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

0:0.07

1:0.06

2:0.08

3:0.09

4:0.08

5:0.08

6:0.07

7:0.09

8:0.10

9:0.06

10:0.08

11:0.08

Negative Logits

ourses

-1.78

 Divinity

-1.68

 realise

-1.66

 Zhou

-1.64

 Dresden

-1.62

 Enhancement

-1.61

 Abilities

-1.56

 Stur

-1.50

theless

-1.48

 Schwar

-1.47

POSITIVE LOGITS

 WATCHED

1.76

 pend

1.58

tain

1.56

 justices

1.52

keye

1.50

pport

1.45

gag

1.45

 knots

1.45

 hears

1.45

osate

1.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.