INDEX

Explanations

instances of social criticism regarding issues of discrimination and injustice

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.02

2:0.07

3:0.31

4:0.03

5:0.09

6:0.01

7:0.07

8:0.06

9:0.01

10:0.17

11:0.03

Negative Logits

ヘラ

-2.41

ノ

-2.18

iameter

-2.12

龍喚士

-2.12

�

-2.10

andise

-2.03

rounded

-2.02

Strength

-1.93

ω

-1.92

ioxide

-1.89

POSITIVE LOGITS

 prosecutions

2.64

 scandals

2.42

 campaigns

2.40

 hurricanes

2.39

 whistleblowers

2.39

 lawsuits

2.39

 scams

2.36

 democracies

2.32

 boycot

2.29

 privat

2.28

Activations Density 0.664%

instances of social criticism regarding issues of discrimination and injustice

No Comments

No Known Activations