INDEX

Explanations

phrases related to regulatory or administrative actions and their implications

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

0:0.06

1:0.02

2:0.05

3:0.42

4:0.02

5:0.08

6:0.04

7:0.05

8:0.03

9:0.04

10:0.11

11:0.03

Negative Logits

 Newspaper

-2.04

 Newsp

-1.95

 SPORTS

-1.93

 Flavoring

-1.93

 pione

-1.86

zbollah

-1.82

ActionCode

-1.73

 Television

-1.71

ibaba

-1.71

senal

-1.67

POSITIVE LOGITS

 theirs

3.42

 hers

2.64

 them

2.61

 yours

2.57

 ones

2.55

 accordingly

2.55

 thereof

2.47

them

2.38

.�

2.29

it

2.27

Activations Density 0.950%

phrases related to regulatory or administrative actions and their implications

No Comments

No Known Activations