INDEX

Explanations

phrases related to lobbying and political coordination

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.11

1:0.03

2:0.05

3:0.04

4:0.05

5:0.05

6:0.24

7:0.02

8:0.07

9:0.23

10:0.01

11:0.04

Negative Logits

 Summit

-4.07

 Primal

-3.80

pit

-3.54

monkey

-3.52

 shaman

-3.39

 Izan

-3.36

jas

-3.36

 titan

-3.35

 Summoner

-3.34

Ram

-3.34

POSITIVE LOGITS

 Fleming

10.98

Fle

9.42

Fle

7.90

 Fleet

5.54

fle

5.46

fle

4.92

 Fisher

4.52

FN

4.29

 Claude

3.91

Lis

3.90

Activations Density 0.001%

phrases related to lobbying and political coordination

No Comments

No Known Activations