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

0:0.07

1:0.08

2:0.08

3:0.08

4:0.08

5:0.08

6:0.07

7:0.10

8:0.06

9:0.08

10:0.09

11:0.08

Negative Logits

 condem

-1.92

PORT

-1.86

CHECK

-1.85

aukee

-1.81

BR

-1.70

 Garmin

-1.63

meter

-1.60

HER

-1.57

amiya

-1.55

PRE

-1.53

POSITIVE LOGITS

 Democr

1.77

 Topics

1.73

 actionGroup

1.69

 Outbreak

1.64

 Coliseum

1.62

inals

1.58

eds

1.58

vernment

1.58

 occupations

1.57

organized

1.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.