INDEX

Explanations

entities and roles related to people involved in incidents or 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

0:0.02

1:0.01

2:0.24

3:0.18

4:0.11

5:0.02

6:0.04

7:0.03

8:0.10

9:0.06

10:0.10

11:0.05

Negative Logits

sbm

-1.64

icity

-1.52

 Playoffs

-1.51

ishers

-1.47

DragonMagazine

-1.46

channelAvailability

-1.45

olars

-1.44

tnc

-1.44

ministic

-1.42

verages

-1.42

POSITIVE LOGITS

 Gest

1.65

ˈ

1.62

 whom

1.59

 extraord

1.59

 discipl

1.57

 fitness

1.52

 birthplace

1.50

 famed

1.50

 fame

1.48

 formerly

1.42

Activations Density 0.240%

entities and roles related to people involved in incidents or conflicts

No Comments

No Known Activations