INDEX

Explanations

phrases indicating time or chronology

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

2:0.10

3:0.09

4:0.38

5:0.02

6:0.04

7:0.06

8:0.03

9:0.03

10:0.11

11:0.07

Negative Logits

ibaba

-1.67

blance

-1.61

itiveness

-1.54

ortality

-1.49

osponsors

-1.47

 Danger

-1.45

IDA

-1.39

appiness

-1.36

 appearances

-1.36

ebus

-1.35

POSITIVE LOGITS

の魔

1.62

actionDate

1.48

 Chung

1.43

Hug

1.43

terday

1.42

 beforehand

1.42

Ago

1.41

retty

1.39

 theat

1.35

 Ples

1.33

Activations Density 0.279%

phrases indicating time or chronology

No Comments

No Known Activations