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

1:0.10

2:0.08

3:0.08

4:0.08

5:0.08

6:0.07

7:0.07

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

 Cardinal

-1.66

 Revelation

-1.59

 presence

-1.48

 proposition

-1.47

 backer

-1.43

 scripture

-1.41

 trickle

-1.40

 sound

-1.39

 falsehood

-1.36

 attack

-1.36

POSITIVE LOGITS

skirts

1.84

acebook

1.78

Da

1.78

OA

1.66

HAHAHAHA

1.64

terms

1.63

count

1.62

aic

1.56

yip

1.51

ommel

1.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.