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

0:0.07

1:0.08

2:0.08

3:0.08

4:0.07

5:0.09

6:0.06

7:0.06

8:0.08

9:0.12

10:0.09

11:0.07

Negative Logits

Klu

-1.69

ECK

-1.51

=[

-1.51

 Puzzle

-1.48

 Retrieved

-1.48

={

-1.47

CHECK

-1.47

 Cheong

-1.43

Pok

-1.43

 Ibid

-1.40

POSITIVE LOGITS

ruary

1.98

natureconservancy

1.87

hya

1.75

inventoryQuantity

1.69

arbon

1.68

luck

1.63

yip

1.61

onian

1.57

ixties

1.54

 Lent

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.