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

1:0.05

2:0.08

3:0.08

4:0.08

5:0.09

6:0.08

7:0.09

8:0.07

9:0.08

10:0.07

11:0.08

Negative Logits

iversary

-1.95

ittee

-1.84

agar

-1.81

pletion

-1.74

ratulations

-1.72

lit

-1.72

mble

-1.71

quartered

-1.71

essert

-1.69

��

-1.68

POSITIVE LOGITS

 multiplier

1.73

Pf

1.64

 Leviathan

1.64

 Unch

1.57

 prevailing

1.57

 exert

1.56

 Winc

1.52

 batting

1.51

 disparate

1.51

 pricing

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.