INDEX

Explanations

phrases related to rivalries and conflicts

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

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

0:0.01

1:0.01

2:0.05

3:0.06

4:0.10

5:0.03

6:0.03

7:0.34

8:0.04

9:0.04

10:0.14

11:0.09

Negative Logits

warning

-1.53

 readings

-1.50

inventoryQuantity

-1.45

Reading

-1.42

doors

-1.41

rieve

-1.41

icter

-1.37

cedented

-1.36

panic

-1.35

LEASE

-1.33

POSITIVE LOGITS

 rivalry

1.72

 masc

1.68

ois

1.58

 feud

1.56

 vend

1.43

 rival

1.41

nexus

1.37

 partisans

1.34

 revenge

1.34

 legends

1.30

Activations Density 0.001%

phrases related to rivalries and conflicts

No Comments

No Known Activations