INDEX

Explanations

instances of names and specific terminology related to entities and classifications

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

0:0.06

1:0.33

2:0.03

3:0.04

4:0.03

5:0.21

6:0.03

7:0.01

8:0.04

9:0.06

10:0.06

11:0.04

Negative Logits

 Votes

-1.91

Squ

-1.86

 ---------

-1.82

spir

-1.75

squ

-1.69

mun

-1.68

District

-1.68

########

-1.65

nces

-1.63

McC

-1.60

POSITIVE LOGITS

art

2.37

artz

2.20

ART

2.18

Art

2.12

ART

1.99

arte

1.95

arts

1.74

Cer

1.68

art

1.67

 Dart

1.67

Activations Density 0.001%

instances of names and specific terminology related to entities and classifications

No Comments

No Known Activations