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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.10

1:0.05

2:0.08

3:0.08

4:0.08

5:0.08

6:0.07

7:0.07

8:0.08

9:0.08

10:0.08

11:0.10

Negative Logits

 optimism

-1.76

actionDate

-1.67

 upbeat

-1.66

 Dalai

-1.66

®

-1.66

 bloggers

-1.58

 Mothers

-1.53

 happier

-1.51

 Marie

-1.50

 flavours

-1.50

POSITIVE LOGITS

imeter

1.77

 repe

1.72

ケ

1.70

execute

1.69

CU

1.61

kef

1.61

 scanner

1.60

cheon

1.56

locks

1.56

 actionGroup

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.