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

2:0.08

3:0.07

4:0.07

5:0.08

6:0.08

7:0.09

8:0.07

9:0.08

10:0.08

11:0.09

Negative Logits

itionally

-1.94

 contributors

-1.58

RC

-1.56

geries

-1.54

 volunteers

-1.54

lease

-1.53

atically

-1.49

endants

-1.47

 informants

-1.46

RS

-1.46

POSITIVE LOGITS

 Madd

1.77

 Tsukuyomi

1.66

 Bridges

1.64

 Appearance

1.62

 Illum

1.57

 Difference

1.54

Newsletter

1.54

displayText

1.53

Fem

1.52

 Dictionary

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.