INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

2:0.10

3:0.07

4:0.07

5:0.08

6:0.08

7:0.08

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

omical

-1.50

アル

-1.46

Magn

-1.44

lees

-1.40

eki

-1.37

 Hera

-1.36

nih

-1.35

 guiActiveUn

-1.32

ebus

-1.31

upiter

-1.30

POSITIVE LOGITS

 scams

1.52

 desper

1.48

 schemes

1.45

 unconditional

1.42

 regard

1.40

 insecure

1.40

 respect

1.39

 compan

1.35

 enterprises

1.33

 opportun

1.32

Activations Density 0.000%

No Known Activations

This feature has no known activations.