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

1:0.10

2:0.09

3:0.07

4:0.08

5:0.06

6:0.09

7:0.07

8:0.08

9:0.07

10:0.10

11:0.06

Negative Logits

hess

-1.79

atars

-1.63

wm

-1.58

abulary

-1.52

condition

-1.49

Miss

-1.49

oji

-1.49

dimension

-1.49

 Sketch

-1.48

height

-1.46

POSITIVE LOGITS

 bribes

1.96

 indirect

1.73

IFT

1.56

 estates

1.56

 motives

1.54

 doses

1.51

 partic

1.50

 behavi

1.50

 GOODMAN

1.50

 instit

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.