INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.1.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

0:0.10

1:0.08

2:0.06

3:0.05

4:0.08

5:0.09

6:0.09

7:0.08

8:0.07

9:0.06

10:0.06

11:0.13

Negative Logits

DragonMagazine

-2.00

idav

-1.97

iquette

-1.94

 Authorization

-1.73

aphael

-1.66

essage

-1.64

friend

-1.61

Reviewer

-1.59

hovah

-1.59

ARR

-1.58

POSITIVE LOGITS

 jobs

1.74

 Rubin

1.71

 Dortmund

1.67

 Ivory

1.60

 gigs

1.58

 Klopp

1.58

 gamble

1.56

tackle

1.54

 stadiums

1.52

 warships

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.