INDEX

Explanations

phrases indicating opposing viewpoints or comparisons

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

0:0.16

1:0.07

2:0.02

3:0.03

4:0.02

5:0.15

6:0.05

7:0.02

8:0.30

9:0.04

10:0.04

11:0.03

Negative Logits

Blocks

-1.68

ETF

-1.63

Psy

-1.63

ヘ

-1.61

syn

-1.60

isconsin

-1.58

 Annotations

-1.58

ston

-1.56

wei

-1.56

Reviewer

-1.52

POSITIVE LOGITS

 secondly

2.04

Secondly

2.02

 obscurity

1.88

 Achilles

1.83

 indifference

1.81

 Secondly

1.74

 cynicism

1.73

versely

1.62

 periphery

1.56

Others

1.56

Activations Density 0.002%

phrases indicating opposing viewpoints or comparisons

No Comments

No Known Activations