INDEX

Explanations

references to military conflict and involvement in war-related actions

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_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.14

1:0.04

2:0.01

3:0.19

4:0.07

5:0.15

6:0.06

7:0.01

8:0.14

9:0.11

10:0.01

11:0.02

Negative Logits

notation

-1.85

akespeare

-1.82

Columb

-1.68

ascript

-1.63

akespe

-1.61

steen

-1.61

brainer

-1.57

mc

-1.53

 McCartney

-1.52

 Myers

-1.49

POSITIVE LOGITS

YPG

2.17

 civilians

2.13

 separatists

2.13

 militants

2.11

 militias

2.08

 snipers

1.99

 looting

1.95

 besie

1.94

 paramilitary

1.92

 civilian

1.88

Activations Density 0.274%

references to military conflict and involvement in war-related actions

No Comments

No Known Activations