INDEX

Explanations

words with specific affixes such as 'ose', 'x', 'o', 'er', 'otic', 'ogen', 'ized', 'st', 'est', 'sap', and 'iens'

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.1.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

0:0.45

1:0.07

2:0.03

3:0.02

4:0.05

5:0.04

6:0.08

7:0.04

8:0.02

9:0.03

10:0.02

11:0.09

Negative Logits

 pestic

-1.98

Accessory

-1.74

 horm

-1.72

 Helpful

-1.71

Asset

-1.71

DragonMagazine

-1.68

 Trance

-1.56

 Reincarn

-1.56

 Uriel

-1.54

 unconventional

-1.53

POSITIVE LOGITS

ailed

1.96

ailable

1.92

ilogy

1.89

ded

1.86

attled

1.85

aged

1.85

ousy

1.80

adies

1.70

issues

1.70

uked

1.69

Activations Density 0.003%

words with specific affixes such as 'ose', 'x', 'o', 'er', 'otic', 'ogen', 'ized', 'st', 'est', 'sap', and 'iens'

No Comments

No Known Activations