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

1:0.05

2:0.08

3:0.08

4:0.09

5:0.09

6:0.08

7:0.09

8:0.08

9:0.07

10:0.09

11:0.09

Negative Logits

Ame

-1.64

aber

-1.59

votes

-1.58

 Prophe

-1.58

 Editorial

-1.46

ahs

-1.46

 Gleaming

-1.45

 Flare

-1.43

ilight

-1.43

ruby

-1.40

POSITIVE LOGITS

uci

1.60

kefeller

1.58

ierrez

1.55

own

1.49

leneck

1.47

 managerial

1.46

puter

1.44

 Mellon

1.42

 redress

1.40

 controlling

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.