INDEX

Explanations

news-related terms and mentions of specific persons or publications

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_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.06

1:0.05

2:0.04

3:0.04

4:0.03

5:0.07

6:0.05

7:0.09

8:0.06

9:0.22

10:0.15

11:0.08

Negative Logits

 Shinji

-1.10

 biologically

-1.10

 fitt

-1.09

 pods

-1.08

 rook

-1.07

 depend

-1.07

 stalk

-1.06

 careg

-1.06

FIELD

-1.06

 neighbour

-1.06

POSITIVE LOGITS

 Journalism

1.35

 Watergate

1.34

 Newsp

1.34

 Editorial

1.28

Newsletter

1.26

 editorial

1.26

Politics

1.22

leases

1.19

 Newspaper

1.17

 publishes

1.15

Activations Density 0.326%

news-related terms and mentions of specific persons or publications

No Comments

No Known Activations