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

0:0.09

1:0.09

2:0.07

3:0.07

4:0.07

5:0.10

6:0.08

7:0.04

8:0.10

9:0.09

10:0.07

11:0.07

Negative Logits

 vigilance

-1.60

 beginnings

-1.54

 propri

-1.53

 reciproc

-1.46

 Inquiry

-1.45

theless

-1.45

 inconvenience

-1.45

 everlasting

-1.44

 enrichment

-1.39

 reckoning

-1.38

POSITIVE LOGITS

arnaev

1.74

zac

1.63

capt

1.58

gart

1.56

zynski

1.56

chwitz

1.55

secut

1.53

ungle

1.52

jug

1.50

team

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.