INDEX

Explanations

No Explanations Found

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

1:0.06

2:0.09

3:0.08

4:0.10

5:0.07

6:0.08

7:0.08

8:0.08

9:0.07

10:0.09

11:0.08

Negative Logits

 signature

-2.03

Rog

-1.73

 obser

-1.67

rah

-1.61

Sov

-1.57

haar

-1.57

ommel

-1.54

axter

-1.53

 signatures

-1.52

ertodd

-1.51

POSITIVE LOGITS

osterone

1.73

ceans

1.71

 Invaders

1.66

 Disorder

1.66

 Causes

1.62

 Shirt

1.61

adoes

1.60

ntil

1.60

 Enemies

1.60

 expelled

1.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.