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

0:0.07

1:0.06

2:0.08

3:0.09

4:0.09

5:0.08

6:0.08

7:0.07

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

fits

-1.98

abet

-1.78

ims

-1.74

abus

-1.64

videos

-1.63

serv

-1.61

riages

-1.58

 compet

-1.53

comings

-1.52

amina

-1.50

POSITIVE LOGITS

Grant

1.85

 Grant

1.61

 Minute

1.49

 Woodward

1.45

WER

1.45

 Harold

1.44

KT

1.41

 Cliff

1.39

 Grizz

1.36

 Lloyd

1.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.