INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.07

3:0.08

4:0.08

5:0.08

6:0.07

7:0.09

8:0.09

9:0.08

10:0.07

11:0.10

Negative Logits

raltar

-3.06

psons

-2.99

 Dunk

-2.75

ら

-2.73

 Wolves

-2.70

グ

-2.69

pees

-2.66

イ

-2.63

 Horses

-2.62

 Nightmares

-2.61

POSITIVE LOGITS

Wil

2.64

taboola

2.57

 Kara

2.52

stroke

2.40

 chau

2.33

 Cisco

2.19

Wil

2.17

tom

2.12

ately

2.10

 Jinping

2.10

Activations Density 0.000%

No Known Activations

This feature has no known activations.