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

0:0.09

1:0.06

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

 Cheong

-1.79

 Quote

-1.79

 Jenner

-1.79

nikov

-1.77

Episode

-1.63

haar

-1.61

item

-1.58

DragonMagazine

-1.57

 Evidence

-1.56

cription

-1.54

POSITIVE LOGITS

 hemor

1.85

 strugg

1.84

 fract

1.75

 forestry

1.72

 FIRE

1.67

 cooperative

1.66

 tremend

1.66

 restart

1.65

 disadvantaged

1.63

 defiant

1.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.