INDEX

Explanations

No Explanations Found

New Auto-Interp

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

0:0.10

1:0.06

2:0.08

3:0.07

4:0.07

5:0.08

6:0.08

7:0.07

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

 ashore

-1.62

 Valiant

-1.54

 Units

-1.53

 Jagu

-1.53

 oversees

-1.52

 Ares

-1.52

 basket

-1.48

opter

-1.47

 Pose

-1.47

 Ples

-1.43

POSITIVE LOGITS

nesota

2.12

icans

1.84

CHAT

1.78

gans

1.68

MSM

1.66

 microbi

1.64

abama

1.56

 neurolog

1.56

insured

1.50

��

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.