INDEX

Explanations

branded product names or trademarked terms

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

2:0.12

3:0.07

4:0.07

5:0.06

6:0.21

7:0.06

8:0.07

9:0.04

10:0.12

11:0.04

Negative Logits

illac

-1.87

 smokes

-1.59

 lookout

-1.59

kefeller

-1.57

ufact

-1.54

eworks

-1.49

 shade

-1.47

aturdays

-1.45

 Corner

-1.42

 Majesty

-1.42

POSITIVE LOGITS

�

1.90

ミ

1.89

ザ

1.83

━

1.65

agic

1.62

�

1.56

rencies

1.54

ago

1.44

�

1.43

ッド

1.42

Activations Density 0.000%

branded product names or trademarked terms

No Comments

No Known Activations