INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.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

0:0.07

1:0.08

2:0.07

3:0.09

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.08

10:0.09

11:0.07

Negative Logits

 Feedback

-3.13

 Volunte

-3.10

\\\\\\\\

-2.81

Liter

-2.71

Dream

-2.67

 Unemployment

-2.63

Surv

-2.62

Interstitial

-2.59

iva

-2.53

 Catch

-2.51

POSITIVE LOGITS

�士

3.53

quet

2.74

pering

2.66

utils

2.61

oche

2.59

 Asia

2.52

 Mits

2.48

 Mosque

2.44

 tallest

2.43

":[

2.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.