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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.09

2:0.09

3:0.08

4:0.08

5:0.07

6:0.07

7:0.08

8:0.08

9:0.07

10:0.09

11:0.07

Negative Logits

 Videos

-1.72

 Awards

-1.67

)?

-1.67

 Typhoon

-1.64

 guiActiveUnfocused

-1.55

Sport

-1.54

Tos

-1.53

)--

-1.53

 Satellite

-1.53

storms

-1.45

POSITIVE LOGITS

 coerc

1.80

draw

1.75

 compe

1.72

 incorpor

1.66

 charact

1.61

 conce

1.56

areth

1.47

holding

1.45

 coupling

1.44

galitarian

1.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.