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

0:0.08

1:0.08

2:0.07

3:0.09

4:0.08

5:0.07

6:0.09

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

iazep

-1.63

jew

-1.56

 plugs

-1.55

 snug

-1.51

 guru

-1.46

 butter

-1.46

 pets

-1.46

 decoration

-1.43

worm

-1.42

 Scroll

-1.40

POSITIVE LOGITS

NetMessage

1.83

 Cortex

1.78

�

1.67

 independ

1.65

years

1.56

independent

1.46

 Elections

1.45

 inception

1.44

 parad

1.44

 JUSTICE

1.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.