INDEX

Explanations

phrases indicating a pattern or frequency of occurrences

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

0:0.01

1:0.01

2:0.09

3:0.06

4:0.06

5:0.02

6:0.13

7:0.29

8:0.02

9:0.03

10:0.08

11:0.13

Negative Logits

¯

-1.57

tainment

-1.54

 GOODMAN

-1.45

 Saul

-1.39

selves

-1.39

 Simulator

-1.38

¢

-1.37

cos

-1.37

 dearly

-1.34

forts

-1.32

POSITIVE LOGITS

 mete

1.49

igham

1.49

 projectiles

1.48

 offenses

1.48

 attacks

1.48

 outbreaks

1.45

omore

1.41

 bombings

1.41

urst

1.39

 disruptive

1.39

Activations Density 0.001%

phrases indicating a pattern or frequency of occurrences

No Comments

No Known Activations