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

0:0.09

1:0.07

2:0.08

3:0.08

4:0.07

5:0.09

6:0.08

7:0.08

8:0.07

9:0.09

10:0.07

11:0.08

Negative Logits

 assassinated

-1.63

 economist

-1.61

 Hallow

-1.58

Beg

-1.57

 Pharmaceutical

-1.55

 Rosenthal

-1.55

 appropriations

-1.53

 cosmetics

-1.53

 affidav

-1.53

 ecology

-1.53

POSITIVE LOGITS

andowski

2.15

pez

2.10

rency

2.10

itivity

2.00

ilee

1.97

ilion

1.96

RANT

1.92

acho

1.87

anse

1.87

oton

1.87

Activations Density 0.000%

No Known Activations

This feature has no known activations.