INDEX

Explanations

phrases indicating discussions about personal and collective experiences or opinions

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

0:0.02

1:0.01

2:0.40

3:0.07

4:0.12

5:0.02

6:0.03

7:0.10

8:0.04

9:0.02

10:0.07

11:0.04

Negative Logits

minimum

-1.63

iveness

-1.56

SPONSORED

-1.50

 Efficiency

-1.43

worthiness

-1.43

 effectiveness

-1.42

odynamics

-1.38

 Entered

-1.35

imilation

-1.33

 Navigation

-1.32

POSITIVE LOGITS

amiliar

1.68

olicited

1.67

 reinforcements

1.66

 unwelcome

1.58

ilaterally

1.57

INGTON

1.53

 mysteriously

1.51

 unexpectedly

1.50

Reloaded

1.47

 Canaver

1.45

Activations Density 0.150%

phrases indicating discussions about personal and collective experiences or opinions

No Comments

No Known Activations