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

1:0.07

2:0.08

3:0.10

4:0.09

5:0.08

6:0.07

7:0.08

8:0.08

9:0.06

10:0.08

11:0.08

Negative Logits

Roh

-1.78

 Ludwig

-1.72

 Armenia

-1.69

 Kazakhstan

-1.65

Gy

-1.61

 Guan

-1.60

 Various

-1.60

 Roger

-1.59

 Oman

-1.58

 Antiqu

-1.58

POSITIVE LOGITS

abre

2.16

thood

2.16

netflix

1.73

Spoiler

1.70

Reviewer

1.70

 guiActiveUn

1.69

claimer

1.66

pedia

1.65

gaard

1.65

kind

1.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.