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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.06

2:0.08

3:0.08

4:0.08

5:0.08

6:0.07

7:0.08

8:0.10

9:0.09

10:0.07

11:0.08

Negative Logits

 Outbreak

-1.84

.):

-1.69

 Hail

-1.52

Dro

-1.50

iaries

-1.49

>)

-1.47

ilo

-1.45

 Warn

-1.44

iera

-1.44

 Huckabee

-1.44

POSITIVE LOGITS

Reviewer

1.77

 nutrit

1.55

 multinational

1.53

 trusts

1.48

 corpor

1.46

FN

1.46

inational

1.46

 spirits

1.44

 trust

1.37

 motions

1.36

Activations Density 0.000%

No Known Activations

This feature has no known activations.