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

0:0.08

1:0.05

2:0.09

3:0.08

4:0.09

5:0.08

6:0.07

7:0.09

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

 langu

-1.74

 overwhelm

-1.61

 pile

-1.52

 overrun

-1.51

 unre

-1.47

 spur

-1.41

ham

-1.39

 forums

-1.39

adelphia

-1.38

forum

-1.38

POSITIVE LOGITS

atonin

1.83

��

1.71

 Learns

1.71

 antioxid

1.68

��

1.64

��

1.62

WORK

1.60

ウス

1.57

Strength

1.57

ionic

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.