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

1:0.12

2:0.08

3:0.08

4:0.07

5:0.07

6:0.07

7:0.08

8:0.08

9:0.06

10:0.08

11:0.07

Negative Logits

 losers

-1.70

reverse

-1.68

\">

-1.64

idy

-1.61

Que

-1.52

Delete

-1.51

Sex

-1.51

コ

-1.50

dirty

-1.48

river

-1.48

POSITIVE LOGITS

 obser

2.12

 eleph

2.01

quartered

1.97

 enthusi

1.91

 confir

1.88

 tremend

1.72

 looph

1.71

 prosec

1.69

NetMessage

1.68

anwhile

1.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.