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

1:0.06

2:0.08

3:0.08

4:0.09

5:0.08

6:0.08

7:0.09

8:0.09

9:0.06

10:0.07

11:0.09

Negative Logits

 warrants

-1.72

IPO

-1.57

 Frem

-1.55

abit

-1.55

-1.51

 pending

-1.48

 uncontrolled

-1.43

 reckless

-1.42

severe

-1.39

 related

-1.38

POSITIVE LOGITS

igham

2.06

sonian

2.04

rift

1.93

 Sphere

1.90

olars

1.81

 Dictionary

1.79

DragonMagazine

1.78

othal

1.72

 Encyclopedia

1.69

ographs

1.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.