INDEX

Explanations

frequency of significant nouns and concepts within various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

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

0:0.02

1:0.01

2:0.19

3:0.08

4:0.21

5:0.04

6:0.07

7:0.10

8:0.02

9:0.05

10:0.08

11:0.06

Negative Logits

���

-1.76

 tremend

-1.76

ocamp

-1.58

udicrous

-1.53

nil

-1.53

livion

-1.52

mint

-1.49

cffff

-1.47

��

-1.45

asio

-1.45

POSITIVE LOGITS

Interstitial

1.61

 relation

1.51

 depends

1.48

 relative

1.46

Reply

1.44

 proceeding

1.41

Decre

1.40

 variables

1.38

 attachments

1.33

,...

1.32

Activations Density 0.063%

frequency of significant nouns and concepts within various contexts

No Comments

No Known Activations