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

0:0.06

1:0.06

2:0.09

3:0.06

4:0.09

5:0.07

6:0.07

7:0.10

8:0.07

9:0.09

10:0.09

11:0.09

Negative Logits

Alternative

-1.79

Tomorrow

-1.79

AAAA

-1.71

INO

-1.68

Revolution

-1.59

Tea

-1.57

��

-1.56

aund

-1.55

FINE

-1.54

Train

-1.54

POSITIVE LOGITS

 GoPro

1.70

Osw

1.64

 doubted

1.57

 gaze

1.53

 disbel

1.52

 shutter

1.52

rost

1.50

 contemplated

1.50

answered

1.49

 hesitation

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.