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

1:0.07

2:0.08

3:0.09

4:0.08

5:0.09

6:0.07

7:0.09

8:0.08

9:0.08

10:0.07

11:0.09

Negative Logits

acus

-2.27

cius

-2.27

insk

-2.23

istar

-2.03

esa

-1.99

ube

-1.98

yang

-1.96

gemony

-1.96

erest

-1.95

utan

-1.93

POSITIVE LOGITS

 spoiler

1.78

KH

1.76

 copied

1.69

 needless

1.69

 EDITION

1.68

 prolific

1.61

 mistaken

1.57

 unreliable

1.56

HIM

1.56

 miscarriage

1.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.