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

1:0.06

2:0.08

3:0.07

4:0.09

5:0.07

6:0.08

7:0.08

8:0.09

9:0.09

10:0.09

11:0.08

Negative Logits

 orally

-1.76

 …"

-1.51

ukong

-1.48

sed

-1.45

aughs

-1.44

umbn

-1.43

andestine

-1.42

fect

-1.38

akeru

-1.38

Dispatch

-1.37

POSITIVE LOGITS

paces

1.55

iquette

1.54

hower

1.51

 Hover

1.49

 "$:/

1.47

BILITIES

1.42

�

1.39

 curves

1.39

 slopes

1.37

 ladder

1.36

Activations Density 0.000%

No Known Activations

This feature has no known activations.