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

0:0.09

1:0.08

2:0.08

3:0.08

4:0.08

5:0.09

6:0.08

7:0.07

8:0.07

9:0.08

10:0.09

11:0.07

Negative Logits

 Arkham

-1.59

 Tales

-1.58

 Scripture

-1.55

 anecdotal

-1.54

 Judaism

-1.53

 Jewish

-1.49

 belief

-1.47

 legends

-1.47

 Crescent

-1.44

 illustrations

-1.44

POSITIVE LOGITS

Sov

2.04

puter

1.92

odo

1.73

osate

1.71

hoe

1.64

ynthesis

1.62

pose

1.58

rex

1.57

 STOP

1.56

oult

1.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.