INDEX

Explanations

references to official policies or ultimatums in a context of negotiation or agreement

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

New Auto-Interp

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

0:0.05

1:0.03

2:0.08

3:0.06

4:0.08

5:0.04

6:0.05

7:0.32

8:0.04

9:0.05

10:0.10

11:0.06

Negative Logits

 Flavoring

-2.21

 Lauder

-1.84

 Vital

-1.56

inges

-1.55

ouched

-1.55

iencies

-1.54

Eug

-1.50

idem

-1.48

Pse

-1.48

aic

-1.46

POSITIVE LOGITS

 reluct

2.01

 withd

1.98

 surrender

1.89

 dilemma

1.84

 unconditional

1.76

 asking

1.76

 arrang

1.74

Option

1.73

otomy

1.67

 parting

1.65

Activations Density 0.000%

references to official policies or ultimatums in a context of negotiation or agreement

No Comments

No Known Activations