INDEX

Explanations

references to local government and political entities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

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

0:0.02

1:0.01

2:0.09

3:0.04

4:0.04

5:0.04

6:0.04

7:0.07

8:0.04

9:0.06

10:0.42

11:0.08

Negative Logits

 Mehran

-1.91

VID

-1.78

cules

-1.73

 Canaver

-1.72

doi

-1.71

 Mechdragon

-1.70

reprene

-1.68

oji

-1.67

 Sanskrit

-1.63

 Sharma

-1.63

POSITIVE LOGITS

 adversely

1.78

ifax

1.74

 STOR

1.74

 defenses

1.72

inventoryQuantity

1.72

 retaliate

1.70

ghazi

1.67

ophobia

1.67

mort

1.64

aples

1.63

Activations Density 0.005%

references to local government and political entities

No Comments

No Known Activations