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

0:0.06

1:0.06

2:0.10

3:0.09

4:0.08

5:0.07

6:0.09

7:0.08

8:0.09

9:0.08

10:0.08

11:0.07

Negative Logits

inventoryQuantity

-1.99

��

-1.79

 Santorum

-1.75

 Trayvon

-1.68

bye

-1.67

 apost

-1.66

peak

-1.58

 fallacy

-1.57

 Boehner

-1.54

 Cantor

-1.52

POSITIVE LOGITS

 Interior

1.95

glers

1.75

Soc

1.71

 Tourism

1.62

ossier

1.56

istrate

1.55

Fin

1.53

[/

1.51

adian

1.50

atem

1.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.