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

Head Attr Weights

0:0.09

1:0.07

2:0.07

3:0.08

4:0.08

5:0.08

6:0.07

7:0.08

8:0.09

9:0.07

10:0.08

11:0.08

Negative Logits

enh

-1.85

shock

-1.81

hex

-1.72

engineering

-1.68

ipple

-1.65

 Laden

-1.63

iannopoulos

-1.59

ibe

-1.58

branded

-1.57

oxin

-1.55

POSITIVE LOGITS

 chores

1.90

 struggle

1.83

 wallets

1.82

 drawer

1.75

 taxp

1.69

 actionGroup

1.68

 peasant

1.66

 pockets

1.66

Reviewer

1.65

 裏�

1.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.