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

1:0.07

2:0.10

3:0.07

4:0.09

5:0.06

6:0.07

7:0.10

8:0.09

9:0.07

10:0.08

11:0.08

Negative Logits

 overcoming

-1.68

 Weber

-1.62

 endured

-1.58

 Rabbi

-1.56

 improv

-1.56

 comedians

-1.53

Max

-1.51

 defeating

-1.48

 Goldman

-1.47

 uncover

-1.46

POSITIVE LOGITS

bian

1.89

 intermedi

1.85

station

1.84

qa

1.78

omorphic

1.75

trak

1.75

glomer

1.75

patient

1.75

ivery

1.74

tical

1.72

Activations Density 0.000%

No Known Activations

This feature has no known activations.