INDEX

Explanations

pronouns and references to individuals, emphasizing personal agency and 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_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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.02

1:0.02

2:0.06

3:0.13

4:0.19

5:0.03

6:0.14

7:0.13

8:0.07

9:0.03

10:0.06

11:0.07

Negative Logits

 Thumbnails

-1.89

thumbnails

-1.53

 Fantasy

-1.45

版

-1.41

══

-1.40

Offline

-1.39

Enh

-1.38

Vector

-1.38

ANC

-1.35

CLUS

-1.31

POSITIVE LOGITS

 bothered

1.68

 chosen

1.43

erous

1.38

 bother

1.37

 seeming

1.30

 bothers

1.28

 spends

1.28

 replied

1.27

 volunteered

1.27

 heck

1.25

Activations Density 0.006%

pronouns and references to individuals, emphasizing personal agency and actions

No Comments

No Known Activations