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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.06

1:0.08

2:0.10

3:0.08

4:0.09

5:0.07

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

grave

-1.60

ignt

-1.44

 Inspector

-1.42

fell

-1.33

rights

-1.32

 Stain

-1.31

 glim

-1.31

 Verse

-1.30

 inspector

-1.27

 Correspond

-1.26

POSITIVE LOGITS

══

1.93

═

1.45

uca

1.43

acca

1.35

utm

1.32

ahoo

1.31

daq

1.30

 sharks

1.28

 attrition

1.22

AZ

1.22

Activations Density 0.000%

No Known Activations

This feature has no known activations.