INDEX

Explanations

references to efforts and actions related to political or social reforms

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

0:0.50

1:0.01

2:0.11

3:0.07

4:0.02

5:0.03

6:0.01

7:0.05

8:0.02

9:0.02

10:0.09

11:0.01

Negative Logits

 spoilers

-2.99

 spoiler

-2.51

 paraph

-2.33

 lett

-2.29

 seating

-2.28

OIL

-2.27

 clauses

-2.26

 indent

-2.20

 certific

-2.19

 prescribing

-2.16

POSITIVE LOGITS

 succeed

3.30

 unsuccessful

3.23

ouble

3.20

successful

3.18

 succeeded

3.00

successfully

2.96

 futile

2.78

 successes

2.75

�

2.66

 Impossible

2.60

Activations Density 0.132%

references to efforts and actions related to political or social reforms

No Comments

No Known Activations