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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.06

2:0.08

3:0.09

4:0.09

5:0.06

6:0.08

7:0.10

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

vation

-1.62

arta

-1.61

Americ

-1.60

 Redemption

-1.59

hya

-1.57

raltar

-1.57

 Compared

-1.51

 Unleashed

-1.50

 Dragonbound

-1.46

 Errors

-1.44

POSITIVE LOGITS

�

1.67

 pending

1.63

 lodging

1.53

ORN

1.52

 lett

1.50

 corpor

1.48

CRE

1.45

fet

1.45

SpaceEngineers

1.44

Frameworks

1.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.