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

1:0.08

2:0.08

3:0.07

4:0.09

5:0.07

6:0.07

7:0.07

8:0.09

9:0.08

10:0.08

11:0.09

Negative Logits

 Roche

-1.63

 successor

-1.63

eer

-1.61

Lv

-1.60

 Defender

-1.59

 Till

-1.55

Hut

-1.50

 Clarks

-1.50

 Elementary

-1.47

 Leap

-1.46

POSITIVE LOGITS

uph

1.87

soType

1.86

watching

1.85

opian

1.83

ominated

1.80

gow

1.72

pedia

1.69

ju

1.68

��

1.66

orney

1.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.