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

0:0.08

1:0.07

2:0.08

3:0.08

4:0.08

5:0.08

6:0.07

7:0.08

8:0.08

9:0.10

10:0.07

11:0.09

Negative Logits

 testers

-1.66

 Taste

-1.53

 flavours

-1.52

 exclusively

-1.50

Reviewed

-1.50

 Surviv

-1.49

 Plants

-1.49

 Trials

-1.48

Critical

-1.44

 Wander

-1.42

POSITIVE LOGITS

Jr

1.96

shaw

1.78

�

1.74

�

1.66

 Jinn

1.64

��

1.61

�

1.60

�

1.60

�

1.57

ificate

1.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.