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

0:0.05

1:0.06

2:0.11

3:0.10

4:0.09

5:0.08

6:0.07

7:0.08

8:0.09

9:0.08

10:0.07

11:0.08

Negative Logits

ibilities

-1.84

comings

-1.68

 repetition

-1.67

camp

-1.65

etheless

-1.60

depend

-1.51

CHAPTER

-1.50

erker

-1.48

ilib

-1.45

itary

-1.45

POSITIVE LOGITS

 Investors

1.97

 Mississ

1.74

 Brands

1.66

 Peel

1.64

 Kens

1.61

Ips

1.51

 Mong

1.50

 Parents

1.48

Shares

1.47

 Scarborough

1.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.