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

2:0.08

3:0.07

4:0.07

5:0.08

6:0.08

7:0.09

8:0.08

9:0.08

10:0.09

11:0.09

Negative Logits

-1.55

lear

-1.51

raft

-1.45

arel

-1.45

aband

-1.44

aneously

-1.44

cept

-1.44

aff

-1.42

inders

-1.39

lov

-1.39

POSITIVE LOGITS

 Gamer

1.76

yssey

1.71

Gamer

1.44

 initialize

1.38

onso

1.33

 Shooter

1.32

 builder

1.30

ptoms

1.28

rul

1.27

 Vulkan

1.27

Activations Density 0.000%

No Known Activations

This feature has no known activations.