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

0:0.08

1:0.07

2:0.09

3:0.08

4:0.09

5:0.05

6:0.08

7:0.09

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

 trillions

-1.60

 cannon

-1.59

 partisans

-1.55

escap

-1.50

 friction

-1.50

 atom

-1.48

 Kirby

-1.48

 centrif

-1.48

Ultra

-1.42

lectic

-1.41

POSITIVE LOGITS

osponsors

2.01

afa

1.86

iann

1.76

aughtered

1.68

icipated

1.67

essor

1.60

itionally

1.56

inson

1.53

pleted

1.52

acebook

1.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.